Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 1434
    Prev
    Next
    INDEX
    Explanations

    words related to Microsoft products or technologies

    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
    314
    +0.12
    0.6%
    294
    +0.11
    0.5%
    508
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    508
    +0.12
    0.02
    538
    +0.11
    0.01
    294
    +0.11
    0.01
    Negative Logits
    rer
    -0.86
    rers
    -0.79
    footed
    -0.69
    redo
    -0.67
    rency
    -0.66
    ============
    -0.66
    ======
    -0.64
     sane
    -0.62
     adjourn
    -0.61
    idate
    -0.61
    POSITIVE LOGITS
    RP
    1.29
    NBC
    1.08
    aunders
    1.03
    DOS
    0.97
    DN
    0.97
    gt
    0.92
    AA
    0.90
    CL
    0.89
    VC
    0.88
    FT
    0.85
    Activations Density 0.022%

    No Known Activations