© 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. 26608
    Prev
    Next
    INDEX
    Explanations

    references to specific years

    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
    480
    +0.14
    0.7%
    256
    +0.11
    0.5%
    376
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    376
    +0.14
    0.03
    146
    +0.11
    0.03
    306
    +0.11
    0.03
    Negative Logits
    instead
    -0.79
    amn
    -0.78
     arrang
    -0.77
     withd
    -0.77
    hops
    -0.75
    prime
    -0.74
    amber
    -0.73
     administr
    -0.73
    lass
    -0.72
    kef
    -0.71
    POSITIVE LOGITS
    å¹
    1.21
     Annual
    0.85
     Edition
    0.81
     edition
    0.81
     Rankings
    0.80
     Update
    0.79
     Salary
    0.79
     Stats
    0.76
    天
    0.76
     Nobel
    0.75
    Activations Density 0.036%

    No Known Activations