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. 23111
    Prev
    Next
    INDEX
    Explanations

    expressions of hope or optimism

    oai_token-act-pair · gpt-4o-miniTriggered 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
    644
    +0.10
    0.5%
    679
    +0.09
    0.4%
    239
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    644
    +0.10
    0.03
    449
    +0.09
    0.02
    8
    +0.09
    0.02
    Negative Logits
    pes
    -0.74
    vation
    -0.66
    kw
    -0.66
    inas
    -0.64
    IDER
    -0.64
    eas
    -0.63
    akable
    -0.62
    atures
    -0.62
    ItemImage
    -0.62
    ces
    -0.61
    POSITIVE LOGITS
     someday
    1.13
     congr
    0.83
     whoever
    0.74
     you
    0.72
     somebody
    0.70
     unborn
    0.69
     readers
    0.69
     expr
    0.66
    fully
    0.66
    reprene
    0.65
    Activations Density 0.024%

    No Known Activations