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. 11706
    Prev
    Next
    INDEX
    Explanations

    expressions of empathy and sympathy regarding a tragic event

    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
    558
    +0.10
    0.5%
    234
    +0.09
    0.4%
    547
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.10
    0.06
    570
    +0.09
    0.01
    526
    +0.09
    -0.01
    Negative Logits
    Newsletter
    -0.69
    govtrack
    -0.63
     Drivers
    -0.63
    bis
    -0.62
    xus
    -0.62
    olin
    -0.61
     Areas
    -0.61
    yden
    -0.60
    coal
    -0.60
     miners
    -0.59
    POSITIVE LOGITS
     suddenly
    0.79
    respected
    0.79
     honestly
    0.78
    ?!"
    0.76
     blatantly
    0.76
     such
    0.74
    ocious
    0.73
     disrespect
    0.73
     senseless
    0.72
    someone
    0.71
    Activations Density 0.637%

    No Known Activations