© 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. 10426
    Prev
    Next
    INDEX
    Explanations

    comma-separated lists of items

    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
    252
    +0.11
    0.5%
    140
    +0.10
    0.5%
    297
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.11
    0.08
    546
    +0.10
    0.08
    140
    +0.09
    0.08
    Negative Logits
    onym
    -0.69
    hei
    -0.68
    ei
    -0.64
    sein
    -0.64
    isse
    -0.63
    ida
    -0.61
    ©¶æ
    -0.59
    ademic
    -0.59
    ole
    -0.59
    sie
    -0.59
    POSITIVE LOGITS
     which
    1.40
     whose
    1.36
    whose
    1.24
    which
    1.22
     wherein
    1.07
     where
    1.07
     whereby
    1.03
     although
    0.98
     who
    0.97
     namely
    0.97
    Activations Density 0.514%

    No Known Activations