© 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. 26566
    Prev
    Next
    INDEX
    Explanations

    references to the UN Security Council and its resolutions

    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
    708
    +0.10
    0.4%
    386
    +0.09
    0.4%
    288
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    708
    +0.10
    0.01
    146
    +0.09
    0.01
    302
    +0.09
    0.01
    Negative Logits
    axter
    -0.82
    href
    -0.79
    ulia
    -0.74
     Weld
    -0.73
    CTV
    -0.71
    ãĤ¨ãĥ«
    -0.71
    icio
    -0.70
    veland
    -0.70
     Manit
    -0.69
    FOX
    -0.68
    POSITIVE LOGITS
     Directive
    1.03
     Resolution
    0.98
     Treaty
    0.92
     Framework
    0.91
     sanctions
    0.91
     resolutions
    0.89
     diplomats
    0.86
     Commission
    0.84
     envoy
    0.84
     unanimously
    0.83
    Activations Density 0.018%

    No Known Activations