© 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. 9266
    Prev
    Next
    INDEX
    Explanations

    processes and methods related to scientific research and observation

    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
    1
    +0.12
    0.5%
    447
    +0.11
    0.5%
    379
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1
    +0.12
    0.05
    665
    +0.11
    0.05
    654
    +0.11
    0.04
    Negative Logits
     Carbuncle
    -0.76
    appointed
    -0.70
     Masquerade
    -0.68
    ovie
    -0.66
    ©¶æ¥µ
    -0.66
     pleading
    -0.64
    bare
    -0.64
    athi
    -0.64
    enty
    -0.64
    quote
    -0.60
    POSITIVE LOGITS
     how
    1.01
     trends
    0.96
     whether
    0.90
     patterns
    0.90
     anomalies
    0.88
     correlations
    0.87
     biomark
    0.83
    itatively
    0.82
     whats
    0.80
     fluctuations
    0.79
    Activations Density 0.239%

    No Known Activations