© 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. 6720
    Prev
    Next
    INDEX
    Explanations

    references to a specific name or term, such as "Dykes"

    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
    99
    +0.10
    0.5%
    659
    +0.10
    0.4%
    121
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.01
    639
    +0.10
    0.01
    659
    +0.10
    0.01
    Negative Logits
    sburgh
    -0.81
    ãĤĤ
    -0.79
     DEFENSE
    -0.72
    OAD
    -0.70
    姫
    -0.70
    ãģĤ
    -0.67
     Whale
    -0.67
    CRIP
    -0.66
     %%
    -0.65
    insula
    -0.63
    POSITIVE LOGITS
    kes
    0.88
    stop
    0.87
    adic
    0.86
    rell
    0.84
    ston
    0.84
    roid
    0.83
    functional
    0.83
    arb
    0.83
    ne
    0.82
    gradation
    0.81
    Activations Density 0.024%

    No Known Activations