© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 32029
    Prev
    Next
    INDEX
    Explanations

    names of individuals

    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
    373
    +0.11
    0.7%
    641
    +0.08
    0.5%
    721
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.11
    0.10
    284
    +0.08
    0.11
    406
    +0.08
    0.10
    Negative Logits
    Rush
    -0.57
     flakes
    -0.53
    Shares
    -0.53
     Klux
    -0.50
    Mobile
    -0.50
    abase
    -0.48
    dylib
    -0.47
    VALUE
    -0.46
    â̦â̦â̦â̦â̦â̦â̦â̦
    -0.46
    Frameworks
    -0.45
    POSITIVE LOGITS
    inis
    0.74
    schild
    0.73
    alam
    0.64
    ais
    0.63
    ini
    0.63
    yne
    0.63
    tes
    0.61
    inas
    0.60
    i
    0.60
    oad
    0.59
    Activations Density 3.767%

    No Known Activations