© 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. 18551
    Prev
    Next
    INDEX
    Explanations

    hyphenated terms and phrases

    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
    373
    +0.14
    0.6%
    62
    +0.09
    0.4%
    83
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    62
    +0.14
    0.02
    537
    +0.09
    0.02
    83
    +0.08
    0.02
    Negative Logits
     omn
    -0.64
     antid
    -0.63
     Helpful
    -0.59
    ãģ®éŃĶ
    -0.59
     quar
    -0.58
     potassium
    -0.58
     academ
    -0.58
     richer
    -0.58
     dense
    -0.57
     intel
    -0.57
    POSITIVE LOGITS
    shirt
    1.34
    shirts
    1.32
    shaped
    1.03
    rex
    1.02
    minus
    0.94
    Rex
    0.93
    mobile
    0.87
    1000
    0.87
    Mobile
    0.84
    Sh
    0.81
    Activations Density 0.025%

    No Known Activations