© 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. 23864
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Reid" in various contexts

    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
    447
    +0.15
    0.7%
    223
    +0.12
    0.6%
    288
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    547
    +0.15
    0.01
    659
    +0.12
    0.01
    443
    +0.11
    0.01
    Negative Logits
    andise
    -0.97
    eatures
    -0.76
     ILCS
    -0.74
    teenth
    -0.71
    omaly
    -0.71
    tesy
    -0.69
    tips
    -0.69
    ruciating
    -0.67
     Kafka
    -0.66
     behav
    -0.64
    POSITIVE LOGITS
    burgh
    0.91
    igan
    0.82
    ifying
    0.77
    elsen
    0.73
     Reid
    0.72
    sburg
    0.72
    ety
    0.71
     Rib
    0.70
    bro
    0.70
    quist
    0.70
    Activations Density 0.014%

    No Known Activations