© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 31101
    Prev
    Next
    INDEX
    Explanations

    mentions of indirect involvement or effects

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.12
    0.6%
    447
    +0.10
    0.5%
    642
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.12
    0.26
    77
    +0.10
    0.08
    448
    +0.09
    0.05
    Negative Logits
    CENT
    -0.82
    ciating
    -0.81
    erk
    -0.79
    imen
    -0.77
    士
    -0.74
    aults
    -0.72
    itton
    -0.69
    avers
    -0.67
    avorite
    -0.64
    ingers
    -0.64
    POSITIVE LOGITS
     indirect
    0.80
     indirectly
    0.75
     sensing
    0.70
     prox
    0.68
    ally
    0.64
    alf
    0.63
     beneficial
    0.62
    ory
    0.62
     somew
    0.61
     illumination
    0.61
    Activations Density 10.597%

    No Known Activations