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. 11774
    Prev
    Next
    INDEX
    Explanations

    connections between individuals in a social context

    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
    401
    +0.12
    0.6%
    502
    +0.10
    0.5%
    433
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.12
    0.04
    502
    +0.10
    0.03
    224
    +0.10
    0.03
    Negative Logits
    imon
    -0.66
    ension
    -0.66
     cess
    -0.62
     NBN
    -0.61
     pH
    -0.61
    uncture
    -0.60
    itor
    -0.59
    Zip
    -0.58
    Specific
    -0.57
     IB
    -0.57
    POSITIVE LOGITS
     alike
    1.06
    mates
    0.99
     were
    0.82
     embarked
    0.79
    mate
    0.76
     are
    0.74
     respectively
    0.73
     intend
    0.72
     sailed
    0.72
    axter
    0.71
    Activations Density 0.128%

    No Known Activations