© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1625
    Prev
    Next
    INDEX
    Explanations

    the word "Gir" followed by a number

    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
    578
    +0.12
    0.5%
    68
    +0.10
    0.5%
    441
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.12
    0.01
    702
    +0.10
    0.01
    738
    +0.10
    0.01
    Negative Logits
    ãĥ¼ãĥĨ
    -0.68
     belt
    -0.64
    ACTED
    -0.63
     solvent
    -0.61
    ãĥĩãĤ£
    -0.60
     Contra
    -0.59
     Sorceress
    -0.59
     Samoa
    -0.57
     fabricated
    -0.57
     Mirror
    -0.57
    POSITIVE LOGITS
    affe
    1.40
    oux
    0.99
    aldi
    0.96
    anges
    0.91
    otta
    0.91
    bage
    0.90
    bons
    0.87
    kees
    0.85
    amel
    0.84
    ardi
    0.84
    Activations Density 0.016%

    No Known Activations