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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 865
    Prev
    Next
    INDEX
    Explanations

    time-related information like dates and time

    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
    373
    +0.27
    1.3%
    601
    +0.10
    0.5%
    525
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.27
    -0.01
    601
    +0.10
    0.04
    296
    +0.09
    0.04
    Negative Logits
     brim
    -0.67
     acknowled
    -0.66
     suits
    -0.64
     totaling
    -0.62
     frequent
    -0.61
     subdiv
    -0.61
     volunteers
    -0.61
     incorpor
    -0.60
     once
    -0.59
     conductor
    -0.59
    POSITIVE LOGITS
    hower
    0.98
     EDT
    0.94
     PDT
    0.88
     EST
    0.86
     GMT
    0.79
     PST
    0.79
     ET
    0.78
     CST
    0.75
     CET
    0.68
    к
    0.66
    Activations Density 0.066%

    No Known Activations