© 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 24576
    9. 8-RES_FS24576-JB
    11. 18907
    Prev
    Next
    INDEX
    Explanations

    terms related to disc golf and specific disc golf equipment

    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
    373
    +0.18
    1.0%
    87
    +0.16
    0.9%
    481
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.18
    0.06
    659
    +0.16
    0.06
    314
    +0.10
    -0.00
    Negative Logits
    )."
    -0.76
    ]."
    -0.74
    .")
    -0.71
     outright
    -0.62
    âĢ¦."
    -0.61
     altogether
    -0.58
     elsewhere
    -0.57
    DERR
    -0.57
    ").
    -0.56
    )].
    -0.56
    POSITIVE LOGITS
     âĵĺ
    0.70
     Edition
    0.70
     (?,
    0.59
     Built
    0.59
     Released
    0.58
    Joined
    0.57
     Poster
    0.56
     Retrieved
    0.54
    ived
    0.52
     Collection
    0.52
    Activations Density 0.645%

    No Known Activations