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. 23052
    Prev
    Next
    INDEX
    Explanations

    mentions of free or complimentary offers

    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
    385
    +0.12
    0.6%
    731
    +0.12
    0.5%
    373
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.12
    0.02
    222
    +0.12
    0.02
    731
    +0.11
    0.01
    Negative Logits
    abal
    -0.93
    amel
    -0.85
    laus
    -0.76
    aukee
    -0.74
    oldemort
    -0.71
    ufact
    -0.71
    itialized
    -0.69
    DERR
    -0.69
     Takeru
    -0.66
    pillar
    -0.65
    POSITIVE LOGITS
     eBook
    1.00
    bie
    0.95
    bies
    0.92
     downloadable
    0.90
     ebook
    0.88
     download
    0.84
     Adobe
    0.83
     subscription
    0.80
     weekly
    0.79
     downloads
    0.78
    Activations Density 0.018%

    No Known Activations