© 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 49152
    9. 8-RES_FS49152-JB
    11. 26612
    Prev
    Next
    INDEX
    Explanations

    references to hierarchical status or ranking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    444
    +0.14
    0.7%
    274
    +0.10
    0.5%
    554
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    444
    +0.14
    0.01
    565
    +0.10
    0.01
    4
    +0.10
    0.01
    Negative Logits
    TERN
    -0.79
    ãģ¦
    -0.73
    SEE
    -0.69
    DAY
    -0.68
    look
    -0.67
    natureconservancy
    -0.65
     Pwr
    -0.64
    keeper
    -0.64
    manship
    -0.63
    giving
    -0.60
    POSITIVE LOGITS
    isions
    1.21
    ski
    1.08
    ille
    1.07
    ania
    1.07
    ision
    1.05
    ideos
    1.05
    itating
    0.99
    iew
    0.99
    oice
    0.96
    idge
    0.95
    Activations Density 0.005%

    No Known Activations