© 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 EvalsExportsinterp-engineNEWAPI 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. 16956
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions or consequences

    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
    35
    +0.15
    0.7%
    665
    +0.13
    0.6%
    620
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    35
    +0.15
    0.02
    665
    +0.13
    0.02
    386
    +0.12
    0.02
    Negative Logits
    omorphic
    -0.91
    omorph
    -0.87
    ãĤ¤ãĥĪ
    -0.73
    groups
    -0.73
    ovie
    -0.70
    population
    -0.69
    ready
    -0.67
    apore
    -0.65
    76561
    -0.65
    ãĤ¨ãĥ«
    -0.65
    POSITIVE LOGITS
     levied
    1.34
    alties
    0.98
     imposed
    0.97
     incurred
    0.95
     fines
    0.94
     owed
    0.88
     penalties
    0.87
     evasion
    0.84
     fined
    0.82
     penalty
    0.81
    Activations Density 0.024%

    No Known Activations