© 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. 37198
    Prev
    Next
    INDEX
    Explanations

    phrases indicating presence or participation in a specific location or situation

    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
    447
    +0.19
    0.9%
    393
    +0.11
    0.5%
    347
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    517
    +0.19
    0.11
    388
    +0.11
    0.10
    679
    +0.10
    0.17
    Negative Logits
     comprom
    -0.62
     powers
    -0.59
     fibers
    -0.55
     CJ
    -0.55
     repr
    -0.55
     Cum
    -0.55
     lymph
    -0.54
    gencies
    -0.54
     FTA
    -0.54
     favour
    -0.53
    POSITIVE LOGITS
    abouts
    1.19
    tical
    0.83
    itored
    0.78
    inel
    0.77
    inar
    0.76
     Somewhere
    0.74
    ngth
    0.72
    upon
    0.68
    çĶŁ
    0.68
    enta
    0.66
    Activations Density 8.800%

    No Known Activations