© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 19633
    Prev
    Next
    INDEX
    Explanations

    phrases related to claiming or asserting responsibility

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    688
    +0.11
    0.5%
    53
    +0.11
    0.5%
    544
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    688
    +0.11
    0.04
    53
    +0.11
    0.04
    274
    +0.10
    0.04
    Negative Logits
    omb
    -0.68
     Watching
    -0.67
     arrang
    -0.67
    ombo
    -0.63
     Selected
    -0.63
    schild
    -0.60
    onen
    -0.59
    gone
    -0.59
     Closed
    -0.58
    watching
    -0.58
    POSITIVE LOGITS
     innocence
    0.89
     responsibility
    0.82
     ownership
    0.77
     asylum
    0.77
     credit
    0.76
     ignorance
    0.75
     respons
    0.74
     falsely
    0.74
     superiority
    0.72
    edly
    0.71
    Activations Density 0.053%

    No Known Activations