Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 11595
    Prev
    Next
    INDEX
    Explanations

    specific formatting patterns within text, such as dates, names, and dollar amounts

    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
    480
    +0.10
    0.5%
    591
    +0.10
    0.5%
    127
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    127
    +0.10
    0.05
    289
    +0.10
    0.01
    326
    +0.09
    0.10
    Negative Logits
     guiName
    -0.92
    etheless
    -0.54
    ãĢIJ
    -0.53
    ":[{"
    -0.53
     (?,
    -0.53
    ãĢİ
    -0.51
     showc
    -0.51
    Published
    -0.49
    ADVERTISEMENT
    -0.47
    [/
    -0.46
    POSITIVE LOGITS
    )."
    1.92
    ?)
    1.89
    ?).
    1.88
    ?),
    1.83
    )
    1.82
    )?
    1.82
    !)
    1.80
    !).
    1.79
    )"
    1.79
    !),
    1.79
    Activations Density 1.283%

    No Known Activations