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

    Neuronpedia

    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. 3425
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of individuals and locations

    oai_token-act-pair · gpt-3.5-turbo
    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
    62
    +0.16
    0.6%
    99
    +0.16
    0.6%
    659
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.16
    0.11
    326
    +0.16
    0.12
    288
    +0.16
    0.14
    Negative Logits
    repre
    -0.94
    oslov
    -0.85
     liability
    -0.83
    ãĤ¦
    -0.82
    inally
    -0.82
    unal
    -0.79
     obligated
    -0.78
     unaff
    -0.76
     withd
    -0.75
     civ
    -0.75
    POSITIVE LOGITS
    ners
    1.38
    ned
    1.35
    ning
    1.14
    fred
    1.08
    nery
    1.06
    zees
    1.05
    sey
    1.03
    coe
    1.01
    mit
    1.00
    mington
    0.98
    Activations Density 2.005%

    No Known Activations