© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 37268
    Prev
    Next
    INDEX
    Explanations

    words related to accountability and responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    98
    +0.13
    0.6%
    577
    +0.12
    0.6%
    118
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    118
    +0.13
    0.01
    98
    +0.12
    0.01
    577
    +0.11
    0.01
    Negative Logits
     NCT
    -0.85
     greets
    -0.75
    ovych
    -0.65
     fronts
    -0.63
    wana
    -0.61
    kson
    -0.60
     Cheong
    -0.60
     unloaded
    -0.60
     Ans
    -0.59
     Bourbon
    -0.57
    POSITIVE LOGITS
    inence
    0.93
    rency
    0.79
    cled
    0.76
    ivable
    0.76
    ivably
    0.75
    ibly
    0.73
    uration
    0.73
    ãĥ´ãĤ¡
    0.73
    cling
    0.72
     perjury
    0.72
    Activations Density 0.013%

    No Known Activations