© 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. 8723
    Prev
    Next
    INDEX
    Explanations

    details of legal incidents involving arrests, charges, and criminal activities

    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
    665
    +0.10
    0.4%
    86
    +0.09
    0.4%
    74
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.10
    0.02
    86
    +0.09
    0.02
    280
    +0.09
    0.02
    Negative Logits
    DragonMagazine
    -0.87
    Tokens
    -0.76
    clips
    -0.74
    warm
    -0.65
    bucks
    -0.62
     Mehran
    -0.61
    TPPStreamerBot
    -0.61
    bilt
    -0.60
    clip
    -0.60
    Parameters
    -0.59
    POSITIVE LOGITS
     felony
    1.23
     misdemeanor
    1.17
     misdem
    1.05
     violating
    0.98
     treason
    0.98
     conspiring
    0.96
     manslaughter
    0.96
     aggravated
    0.94
    holding
    0.92
     tresp
    0.89
    Activations Density 0.035%

    No Known Activations