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 6144
    5. 8-RES_FS6144-JB
    6. 5480
    Prev
    Next
    INDEX
    Explanations

    adjectives and adverbs indicating opinions or emotions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    +0.10
    0.4%
    588
    +0.09
    0.4%
    63
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    429
    +0.10
    0.06
    271
    +0.09
    0.05
    311
    +0.09
    0.01
    Negative Logits
    ajor
    -0.78
    Downloadha
    -0.78
    iggurat
    -0.72
    rio
    -0.71
    Ó
    -0.71
    obook
    -0.68
    à©
    -0.68
    iper
    -0.67
    authorized
    -0.67
    ailable
    -0.67
    POSITIVE LOGITS
    ly
    1.17
    nesses
    1.01
     enough
    0.99
    ness
    0.95
     Enough
    0.91
    LY
    0.89
     Thoughts
    0.84
     additions
    0.83
     considerations
    0.78
     Ways
    0.77
    Activations Density 0.937%

    No Known Activations