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. 1051
    Prev
    Next
    INDEX
    Explanations

    dates or time periods within text

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    269
    +0.11
    0.5%
    545
    +0.10
    0.4%
    603
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    269
    +0.11
    0.02
    603
    +0.10
    0.03
    494
    +0.09
    0.03
    Negative Logits
    inguished
    -0.78
    apego
    -0.76
    ersive
    -0.74
    sers
    -0.73
    ittee
    -0.67
    oppable
    -0.67
    ourge
    -0.65
    icts
    -0.64
    hyde
    -0.64
    andum
    -0.64
    POSITIVE LOGITS
     mornings
    1.04
     afternoon
    1.02
     adolescence
    0.91
     autumn
    0.91
     evenings
    0.88
     infancy
    0.88
     twenties
    0.87
     morning
    0.87
     October
    0.87
     April
    0.86
    Activations Density 0.040%

    No Known Activations