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. 19302
    Prev
    Next
    INDEX
    Explanations

    technical terms related to renewable energy and healthcare legislation

    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
    41
    +0.11
    0.5%
    439
    +0.10
    0.5%
    364
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    364
    +0.11
    0.03
    392
    +0.10
    0.04
    326
    +0.10
    0.03
    Negative Logits
     skelet
    -0.84
     opin
    -0.74
     independ
    -0.71
     Lutheran
    -0.69
     Volks
    -0.67
     showc
    -0.66
     neigh
    -0.66
     Lauder
    -0.65
     Palestin
    -0.65
     dexter
    -0.64
    POSITIVE LOGITS
    ),
    1.02
    )—
    1.00
    )
    1.00
    )?
    0.94
    +)
    0.92
    ).
    0.88
    ),"
    0.88
    Gs
    0.87
    )-
    0.85
    Fs
    0.85
    Activations Density 0.078%

    No Known Activations