© 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. 3186
    Prev
    Next
    INDEX
    Explanations

    special characters, numbers, and non-English characters

    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
    346
    +0.14
    0.6%
    163
    +0.12
    0.5%
    659
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    103
    +0.14
    0.03
    346
    +0.12
    0.02
    57
    +0.11
    0.02
    Negative Logits
     Leban
    -0.92
    ãĥ¼ãĥĨãĤ£
    -0.85
     responsive
    -0.84
    IFIED
    -0.82
     amplification
    -0.80
    dayName
    -0.76
     outgoing
    -0.75
     nomine
    -0.75
     calendars
    -0.74
     confessions
    -0.73
    POSITIVE LOGITS
    Ĭ±
    1.43
    Ń·
    1.27
    ¶ħ
    1.26
    ¥
    1.21
    ¨
    1.19
    ®
    1.18
    ģĸ
    1.18
    ²
    1.17
    ĩ
    1.16
    ı
    1.15
    Activations Density 0.264%

    No Known Activations