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. 21341
    Prev
    Next
    INDEX
    Explanations

    unique characters or symbol patterns found in language

    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
    87
    +0.15
    0.8%
    176
    +0.12
    0.6%
    592
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.15
    0.04
    326
    +0.12
    0.04
    45
    +0.09
    0.03
    Negative Logits
    onnaissance
    -0.66
     spoilers
    -0.61
    atform
    -0.59
     glitches
    -0.58
     cryptography
    -0.57
     billboards
    -0.57
     privately
    -0.56
    ymm
    -0.55
     concede
    -0.54
     secretly
    -0.53
    POSITIVE LOGITS
    )).
    0.87
    """
    0.83
    endif
    0.83
    "}
    0.82
    ))))
    0.79
    '."
    0.79
    )))
    0.77
    "/>
    0.77
    )."
    0.76
    }.
    0.76
    Activations Density 0.264%

    No Known Activations