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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 816
    Prev
    Next
    INDEX
    Explanations

    specific speeds and measurements like miles per hour

    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
    497
    +0.11
    0.5%
    27
    +0.11
    0.5%
    495
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    495
    +0.11
    0.04
    507
    +0.11
    0.04
    35
    +0.10
    0.04
    Negative Logits
    iture
    -0.84
    folios
    -0.81
     coffers
    -0.73
     Contracts
    -0.72
    ById
    -0.71
    Missing
    -0.71
     Emblem
    -0.70
     Archives
    -0.70
     entitlement
    -0.69
     Cosponsors
    -0.69
    POSITIVE LOGITS
     altitude
    1.02
     Celsius
    0.95
     Hz
    0.92
     rpm
    0.90
     temperatures
    0.90
     temperature
    0.88
     oscill
    0.88
     volts
    0.87
    perature
    0.87
     Fahrenheit
    0.86
    Activations Density 0.210%

    No Known Activations