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. 45962
    Prev
    Next
    INDEX
    Explanations

    dates and specific 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
    321
    +0.11
    0.5%
    185
    +0.10
    0.5%
    218
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.11
    0.04
    310
    +0.10
    0.03
    306
    +0.10
    0.03
    Negative Logits
     purs
    -0.71
    bledon
    -0.68
     lining
    -0.64
    soDeliveryDate
    -0.61
    merce
    -0.61
     masse
    -0.61
     stall
    -0.60
     sights
    -0.60
    entimes
    -0.59
     purse
    -0.59
    POSITIVE LOGITS
     08
    0.76
     Views
    0.74
     Topic
    0.73
    oru
    0.73
     04
    0.72
    iatus
    0.71
     Quote
    0.71
    malink
    0.70
     Posts
    0.70
    posted
    0.69
    Activations Density 0.062%

    No Known Activations