© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 12555
    Prev
    Next
    INDEX
    Explanations

    special characters or non-English letters like "á", "æ", "âĢ", and "ç" in the text

    oai_token-act-pair · gpt-3.5-turbo

    words containing the letter "æ" or similar special characters

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    703
    +0.03
    0.6%
    383
    +0.02
    0.5%
    14
    +0.02
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.03
    0.02
    284
    +0.02
    0.02
    232
    +0.02
    0.02
    Negative Logits
    illac
    -0.17
    hurst
    -0.16
    Attach
    -0.15
    wan
    -0.15
    ollar
    -0.15
    charges
    -0.15
    adra
    -0.14
    rats
    -0.14
    iah
    -0.14
    DOS
    -0.14
    POSITIVE LOGITS
    ãĥ¼ãĥĨ
    0.20
     proport
    0.19
     occas
    0.19
    ccording
    0.18
     Pompe
    0.17
     ende
    0.16
     Dise
    0.16
     Myster
    0.16
     unfocusedRange
    0.15
     proble
    0.15
    Activations Density 0.128%

    No Known Activations