© 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. 10740
    Prev
    Next
    INDEX
    Explanations

    text related to geographical features and measurements

    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
    393
    +0.14
    0.6%
    373
    +0.10
    0.4%
    506
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    506
    +0.14
    0.03
    611
    +0.10
    0.03
    393
    +0.09
    0.03
    Negative Logits
    dayName
    -0.74
    Quantity
    -0.66
    ants
    -0.65
     Picks
    -0.62
    Ô
    -0.61
    opp
    -0.61
    ricanes
    -0.59
    Jan
    -0.59
     Cosponsors
    -0.59
     starters
    -0.57
    POSITIVE LOGITS
    insula
    0.76
     coastline
    0.67
     the
    0.63
     scenery
    0.61
     life
    0.59
     roadway
    0.58
    Ĥ¬
    0.58
    fleet
    0.57
    ij士
    0.57
     town
    0.57
    Activations Density 0.085%

    No Known Activations