© 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. 7491
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions and demands

    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
    679
    +0.10
    0.5%
    393
    +0.10
    0.5%
    504
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.10
    0.03
    705
    +0.10
    0.03
    263
    +0.10
    0.02
    Negative Logits
    ãĥĦ
    -0.79
    ãĤ§
    -0.78
    STAR
    -0.68
    fman
    -0.67
    ãĤ´ãĥ³
    -0.64
    ãĥ¬
    -0.64
    ãĤ¨ãĥ«
    -0.64
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.64
    NAS
    -0.63
    ãĥīãĥ©
    -0.62
    POSITIVE LOGITS
    soever
    0.82
    chers
    0.74
     borrowers
    0.72
     visitors
    0.72
     recipients
    0.72
     policymakers
    0.72
     applicants
    0.71
     travelers
    0.71
     whoever
    0.71
     motorists
    0.68
    Activations Density 0.075%

    No Known Activations