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 6144
    5. 8-RES_FS6144-JB
    6. 5338
    Prev
    Next
    INDEX
    Explanations

    instructions related to setting up a programming environment

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    +0.13
    0.6%
    525
    +0.10
    0.5%
    326
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.08
    500
    +0.10
    0.05
    435
    +0.10
    0.03
    Negative Logits
    agher
    -0.74
     Syndrome
    -0.73
    selling
    -0.69
     funer
    -0.69
    hol
    -0.68
     airs
    -0.67
    rosso
    -0.67
    LOS
    -0.66
     diminishing
    -0.66
     stunts
    -0.66
    POSITIVE LOGITS
     folder
    1.58
     ~/.
    1.47
     file
    1.44
     directory
    1.40
    folder
    1.27
     ~/
    1.27
     executable
    1.23
     repository
    1.23
     files
    1.23
    file
    1.19
    Activations Density 0.748%

    No Known Activations