© 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. 9152
    Prev
    Next
    INDEX
    Explanations

    references to legal charges and criminal allegations

    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
    444
    +0.13
    0.6%
    699
    +0.11
    0.5%
    267
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.02
    444
    +0.11
    0.02
    201
    +0.10
    0.01
    Negative Logits
    yright
    -0.90
    TRY
    -0.81
    itude
    -0.74
    matically
    -0.74
    OWER
    -0.73
    atively
    -0.73
    LET
    -0.72
    wear
    -0.72
    owers
    -0.71
    opher
    -0.70
    POSITIVE LOGITS
     Sabha
    1.16
     nerv
    0.86
     Pradesh
    0.85
     Yug
    0.84
    akov
    0.78
    ption
    0.76
     Nik
    0.76
     Suk
    0.76
    ÄŁ
    0.75
    ccess
    0.74
    Activations Density 0.030%

    No Known Activations