© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 5264
    Prev
    Next
    INDEX
    Explanations

    references to "will", particularly addressing intent or decision-making

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    721
    +0.16
    0.5%
    18
    +0.15
    0.5%
    339
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.16
    0.10
    339
    +0.15
    0.06
    367
    +0.14
    0.07
    Negative Logits
    ¥µ
    -1.22
    ħĭ
    -1.06
     certific
    -1.01
    ĻĤ
    -0.97
    anca
    -0.93
    etheless
    -0.93
    EStreamFrame
    -0.93
    yrinth
    -0.91
    Ĥª
    -0.90
    taboola
    -0.89
    POSITIVE LOGITS
    power
    1.33
    sburg
    1.22
    ows
    1.14
    fulness
    1.12
    ingham
    1.09
    lessness
    1.01
    liam
    0.99
    ful
    0.98
    yers
    0.97
    imil
    0.95
    Activations Density 1.722%

    No Known Activations