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. 378
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns

    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
    481
    +0.15
    0.7%
    551
    +0.12
    0.6%
    457
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.15
    0.06
    566
    +0.12
    0.06
    571
    +0.12
    0.06
    Negative Logits
     Peak
    -0.70
    advertisement
    -0.67
     Millennium
    -0.61
    ione
    -0.60
     School
    -0.59
     Replacement
    -0.57
    Champ
    -0.57
     Gutenberg
    -0.57
     Kinder
    -0.57
     Lift
    -0.57
    POSITIVE LOGITS
    'll
    1.20
     nevertheless
    1.12
     hereby
    1.12
    'd
    0.99
    've
    0.98
     nonetheless
    0.93
     wondered
    0.89
    eded
    0.88
     decided
    0.88
     sugg
    0.86
    Activations Density 0.189%

    No Known Activations