© 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 EvalsExportsinterp-engineNEWAPI 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. 11725
    Prev
    Next
    INDEX
    Explanations

    words related to hobbies and taboos

    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
    640
    +0.04
    0.6%
    253
    +0.03
    0.5%
    706
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.04
    0.03
    326
    +0.03
    0.02
    401
    +0.03
    0.02
    Negative Logits
    meet
    -0.22
    scl
    -0.21
    displayText
    -0.21
    assetsadobe
    -0.21
    iosity
    -0.20
    20439
    -0.20
    ername
    -0.20
    soType
    -0.19
    maxwell
    -0.19
    edd
    -0.19
    POSITIVE LOGITS
    ized
    0.21
    ised
    0.19
     footnote
    0.19
     hol
    0.18
     fetish
    0.18
     significance
    0.18
     HAL
    0.18
     disclaimer
    0.17
    izations
    0.17
    ization
    0.17
    Activations Density 0.047%

    No Known Activations