© 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. 10768
    Prev
    Next
    INDEX
    Explanations

    phrases indicating challenges, difficulties, or obstacles

    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
    608
    +0.19
    0.9%
    273
    +0.10
    0.4%
    210
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.19
    0.04
    210
    +0.10
    0.02
    119
    +0.10
    0.02
    Negative Logits
    querque
    -0.77
     Accessed
    -0.74
    BACK
    -0.69
    cles
    -0.68
    iano
    -0.67
    afety
    -0.67
     teasp
    -0.66
     Powered
    -0.66
    ersed
    -0.65
    ONSORED
    -0.65
    POSITIVE LOGITS
     anyone
    1.19
     anybody
    1.11
     outsiders
    1.10
     opponents
    1.02
     inexperienced
    0.96
     us
    0.94
     adversaries
    0.94
     them
    0.93
     newcomers
    0.92
     competitors
    0.90
    Activations Density 0.061%

    No Known Activations