Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 1233
    Prev
    Next
    INDEX
    Explanations

    time-related actions and durations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    314
    +0.12
    0.5%
    511
    +0.11
    0.5%
    344
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.12
    0.12
    223
    +0.11
    0.09
    269
    +0.10
    0.07
    Negative Logits
     Caption
    -0.60
    Tro
    -0.58
    ilde
    -0.57
    gall
    -0.56
    ollo
    -0.56
    brow
    -0.55
     redistributed
    -0.54
     follower
    -0.54
    ranch
    -0.53
    erers
    -0.53
    POSITIVE LOGITS
     awhile
    1.43
     eternity
    1.19
     longer
    1.16
     hours
    1.15
     decades
    1.15
     periods
    1.13
     weeks
    1.11
     years
    1.10
     months
    1.10
     millennia
    1.08
    Activations Density 1.986%

    No Known Activations