© 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. 37183
    Prev
    Next
    INDEX
    Explanations

    words related to science fiction and technology

    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
    +0.21
    0.9%
    379
    +0.11
    0.4%
    160
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.21
    0.44
    160
    +0.11
    0.31
    393
    +0.10
    0.42
    Negative Logits
     Seat
    -0.91
    ecause
    -0.80
     unfocusedRange
    -0.76
     lapse
    -0.75
    zona
    -0.73
     misdem
    -0.73
     jurisdictions
    -0.72
     miscar
    -0.72
     Areas
    -0.71
    ADRA
    -0.71
    POSITIVE LOGITS
    redo
    0.91
    Talk
    0.89
    prom
    0.88
    talk
    0.86
    oriented
    0.84
    destruct
    0.83
    Dispatch
    0.82
    uden
    0.78
    associated
    0.78
    inspired
    0.77
    Activations Density 28.820%

    No Known Activations