© 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. 41809
    Prev
    Next
    INDEX
    Explanations

    terms related to national and international issues

    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
    +0.25
    1.2%
    447
    +0.23
    1.1%
    87
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    464
    +0.25
    0.04
    345
    +0.23
    0.04
    266
    +0.14
    0.03
    Negative Logits
     Niet
    -0.73
    enegger
    -0.67
    lyak
    -0.66
     Peb
    -0.65
     Borders
    -0.64
     Reilly
    -0.64
     Genie
    -0.64
     Frie
    -0.64
     Bye
    -0.64
    #$
    -0.63
    POSITIVE LOGITS
     ][
    0.79
     ]
    0.77
     ><
    0.65
     |
    0.64
     );
    0.63
     )
    0.63
     ·
    0.62
     ];
    0.62
     ):
    0.62
    _
    0.61
    Activations Density 0.090%

    No Known Activations