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

    Neuronpedia

    Jacobian LensNEW
    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. 7475
    Prev
    Next
    INDEX
    Explanations

    instances of willingness or reluctance to take specific actions or stances

    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
    195
    +0.12
    0.5%
    7
    +0.10
    0.5%
    204
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.12
    0.03
    624
    +0.10
    0.02
    195
    +0.10
    0.01
    Negative Logits
     Surv
    -0.83
     Wrap
    -0.73
    MpServer
    -0.72
     Tid
    -0.72
    verbs
    -0.71
     Gleaming
    -0.68
    unes
    -0.68
    ordon
    -0.65
    76561
    -0.63
    nesium
    -0.63
    POSITIVE LOGITS
    lessness
    0.90
     willingness
    0.86
     unwillingness
    0.82
     adherence
    0.81
     attitude
    0.81
    jriwal
    0.79
     rate
    0.77
    fulness
    0.76
     compliance
    0.72
     refusal
    0.72
    Activations Density 0.064%

    No Known Activations