© 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. 22151
    Prev
    Next
    INDEX
    Explanations

    references to significant entities or events, particularly in the context of business and industry

    oai_token-act-pair · gpt-4o-miniTriggered 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
    129
    +0.10
    0.5%
    288
    +0.10
    0.4%
    41
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.08
    40
    +0.10
    0.04
    129
    +0.09
    0.04
    Negative Logits
     Parables
    -0.68
    gently
    -0.67
    mates
    -0.64
    İĭ
    -0.64
     Jinn
    -0.63
     Keller
    -0.60
    Kind
    -0.59
    ©¶æ
    -0.58
    pered
    -0.58
     Cust
    -0.58
    POSITIVE LOGITS
     (>
    1.14
     conglomer
    0.88
     looms
    0.71
     chunk
    0.70
     multinational
    0.70
     undertaking
    0.68
     congr
    0.68
     swath
    0.67
     eg
    0.66
     conglomerate
    0.65
    Activations Density 0.426%

    No Known Activations