© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 32827
    Prev
    Next
    INDEX
    Explanations

    references to beauty pageants and related events

    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
    323
    +0.14
    0.5%
    491
    +0.13
    0.5%
    643
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    649
    +0.14
    0.03
    123
    +0.13
    0.06
    643
    +0.13
    0.04
    Negative Logits
     brim
    -0.88
    CAST
    -0.82
    ©¶æ
    -0.81
    rd
    -0.77
    Reviewed
    -0.77
    OUGH
    -0.76
    OPLE
    -0.75
     isolate
    -0.74
     agitated
    -0.73
    EStreamFrame
    -0.72
    POSITIVE LOGITS
    ouri
    1.29
    pelling
    1.06
    pelled
    1.03
    hap
    1.02
    ippi
    0.98
    oria
    0.97
     Militia
    0.96
    Miss
    0.95
    pell
    0.93
    enger
    0.92
    Activations Density 5.179%

    No Known Activations