© 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 Local
    9. 6-RES_SCL-AJT
    11. 32221
    Prev
    Next
    INDEX
    Explanations

    mentions of specific car models

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    343
    +0.06
    0.6%
    4
    +0.05
    0.5%
    616
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    95
    +0.06
    0.06
    444
    +0.05
    0.05
    379
    +0.05
    0.11
    Negative Logits
    DEM
    -0.38
    WIND
    -0.35
    PLAY
    -0.33
    LA
    -0.31
    PROV
    -0.30
    lust
    -0.30
    PASS
    -0.29
    Ell
    -0.29
    QUEST
    -0.29
     compliant
    -0.29
    POSITIVE LOGITS
    aurus
    0.48
    borgh
    0.47
    illo
    0.47
    ini
    0.43
    olini
    0.43
    inis
    0.43
    aundering
    0.42
    enhagen
    0.40
    agus
    0.40
    iazep
    0.39
    Activations Density 8.891%

    No Known Activations