© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7993
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to national identities or landmarks

    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
    752
    +0.10
    0.4%
    288
    +0.10
    0.4%
    327
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.10
    0.03
    616
    +0.10
    0.02
    667
    +0.09
    0.02
    Negative Logits
    ullivan
    -0.77
    enger
    -0.74
    areth
    -0.71
     Scand
    -0.69
    eva
    -0.69
    redd
    -0.66
    hou
    -0.66
    rox
    -0.65
    bane
    -0.65
    ered
    -0.65
    POSITIVE LOGITS
     Geographic
    1.08
    ity
    1.01
    ities
    0.91
    unity
    0.85
    ITY
    0.83
     Monument
    0.80
     Rifle
    0.80
    istic
    0.79
    ism
    0.79
    icol
    0.78
    Activations Density 0.021%

    No Known Activations