© 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 12288
    9. 8-RES_FS12288-JB
    11. 1829
    Prev
    Next
    INDEX
    Explanations

    names and locations related to criminal cases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    496
    +0.10
    0.5%
    582
    +0.10
    0.4%
    105
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.10
    0.08
    232
    +0.10
    0.08
    284
    +0.09
    0.07
    Negative Logits
    Rush
    -0.58
     scratch
    -0.58
    Freedom
    -0.58
    keyes
    -0.58
     mainline
    -0.57
     brood
    -0.57
     Breaker
    -0.57
     Breaking
    -0.56
     forge
    -0.56
     fact
    -0.55
    POSITIVE LOGITS
    icz
    1.29
    idis
    1.11
    akis
    1.07
    xual
    1.06
    oulos
    1.06
    i
    1.03
    opoulos
    0.98
    iev
    0.98
    uez
    0.97
    pta
    0.96
    Activations Density 0.457%

    No Known Activations