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 49152
    5. 8-RES_FS49152-JB
    6. 26087
    Prev
    Next
    INDEX
    Explanations

    mentions of the number "19" or related temporal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    253
    +0.12
    0.5%
    746
    +0.11
    0.5%
    220
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    220
    +0.12
    0.02
    693
    +0.11
    0.02
    239
    +0.10
    0.02
    Negative Logits
    anguage
    -0.78
    orc
    -0.78
    aminer
    -0.77
    ensional
    -0.71
    ovie
    -0.71
    iated
    -0.70
    heed
    -0.70
    oaded
    -0.66
     Uriel
    -0.64
    pora
    -0.63
    POSITIVE LOGITS
    th
    1.09
    âĸĪâĸĪ
    0.99
    03
    0.92
    08
    0.91
    059
    0.91
    05
    0.90
    09
    0.90
    06
    0.89
    07
    0.89
    61
    0.89
    Activations Density 0.019%

    No Known Activations