© 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. 18904
    Prev
    Next
    INDEX
    Explanations

    information related to the technical specifications and features of hardware products

    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
    447
    +0.20
    0.9%
    481
    +0.17
    0.8%
    343
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.20
    0.07
    267
    +0.17
    0.05
    45
    +0.10
    0.03
    Negative Logits
    ivals
    -0.82
    Topic
    -0.72
    ecided
    -0.70
     Crusade
    -0.70
    Americ
    -0.70
    Ask
    -0.69
     boycott
    -0.69
    javascript
    -0.66
    polit
    -0.66
    anon
    -0.66
    POSITIVE LOGITS
     protr
    1.24
     sleek
    1.15
     curved
    1.03
     neatly
    1.01
     elong
    1.01
     curves
    0.99
     sculpt
    0.96
     meticulously
    0.94
     adorned
    0.94
     angular
    0.93
    Activations Density 0.561%

    No Known Activations