© 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. 13443
    Prev
    Next
    INDEX
    Explanations

    verbs related to leading or guiding actions

    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
    +0.11
    0.5%
    291
    +0.11
    0.5%
    290
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    324
    +0.11
    0.03
    665
    +0.11
    0.04
    526
    +0.10
    0.00
    Negative Logits
     nick
    -0.63
    pots
    -0.61
    BN
    -0.60
    etheless
    -0.58
     excuses
    -0.58
    âĶĢâĶĢâĶĢâĶĢ
    -0.58
     collateral
    -0.56
     Confeder
    -0.56
     lett
    -0.54
     tipped
    -0.54
    POSITIVE LOGITS
     toward
    1.07
     towards
    1.01
     onward
    0.91
     onwards
    0.84
     into
    0.83
     footsteps
    0.79
     Steps
    0.78
     Towards
    0.78
     uphill
    0.77
    into
    0.77
    Activations Density 0.182%

    No Known Activations