© 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. 32460
    Prev
    Next
    INDEX
    Explanations

    terms related to alliances and partnerships

    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
    447
    +0.14
    0.8%
    0
    +0.09
    0.5%
    525
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    261
    +0.14
    0.06
    623
    +0.09
    0.04
    307
    +0.08
    0.06
    Negative Logits
    lda
    -0.60
     Notting
    -0.56
    orters
    -0.55
     Bengals
    -0.54
     Gemini
    -0.54
     Parenthood
    -0.53
    olicy
    -0.52
     Moonlight
    -0.52
    riz
    -0.51
    liest
    -0.51
    POSITIVE LOGITS
     speaking
    0.68
     minded
    0.66
    uminum
    0.59
    IAS
    0.57
    cock
    0.54
    psey
    0.53
     Speaking
    0.53
    adjust
    0.52
    pheus
    0.52
    gage
    0.52
    Activations Density 8.638%

    No Known Activations