© 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. 34709
    Prev
    Next
    INDEX
    Explanations

    mentions of talented individuals and their abilities or accomplishments

    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
    391
    +0.08
    0.5%
    339
    +0.08
    0.5%
    63
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.08
    0.19
    154
    +0.08
    0.18
    404
    +0.08
    0.14
    Negative Logits
    ptions
    -0.60
    ocaust
    -0.52
    phrine
    -0.48
    Sov
    -0.46
     condol
    -0.45
     abolished
    -0.43
    xon
    -0.43
    8000
    -0.43
    ablishment
    -0.43
    ptive
    -0.42
    POSITIVE LOGITS
    ness
    0.63
    nesses
    0.62
    heet
    0.62
     talents
    0.58
    oso
    0.56
    lings
    0.54
    ayson
    0.53
    umbers
    0.53
     composer
    0.51
    itialized
    0.51
    Activations Density 11.122%

    No Known Activations