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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 34761
    Prev
    Next
    INDEX
    Explanations

    instances of mentions of death or dying in various contexts

    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
    447
    +0.29
    1.2%
    383
    +0.17
    0.7%
    319
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.29
    0.15
    486
    +0.17
    0.06
    142
    +0.16
    0.12
    Negative Logits
    orney
    -0.93
    iola
    -0.85
    rupulous
    -0.84
    Allen
    -0.82
    MN
    -0.81
    Union
    -0.81
    arov
    -0.80
    Ĭ
    -0.79
    Ľ
    -0.78
    OPER
    -0.77
    POSITIVE LOGITS
     horribly
    1.22
     tragically
    0.97
     toll
    0.96
     miser
    0.95
     intest
    0.94
    ffen
    0.93
     peacefully
    0.92
    getic
    0.86
     prematurely
    0.85
     psychiat
    0.84
    Activations Density 8.736%

    No Known Activations