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. 23362
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the beginning of an action or event

    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
    62
    +0.11
    0.5%
    735
    +0.10
    0.5%
    339
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    62
    +0.11
    0.03
    122
    +0.10
    0.03
    545
    +0.10
    0.02
    Negative Logits
    itsch
    -0.88
    cedented
    -0.76
    vertisement
    -0.70
    abyte
    -0.68
    mens
    -0.68
    ilty
    -0.66
    hooting
    -0.66
    holding
    -0.66
    ombat
    -0.65
    igent
    -0.64
    POSITIVE LOGITS
     anew
    0.95
    strap
    0.71
     XI
    0.70
    points
    0.70
     salaries
    0.65
     point
    0.65
    ribune
    0.64
     Gutenberg
    0.61
     inference
    0.59
     fires
    0.58
    Activations Density 0.043%

    No Known Activations