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 3072
    5. 8-RES_FS3072-JB
    6. 668
    Prev
    Next
    INDEX
    Explanations

    words related to intelligence, cognitive abilities, genetic and environmental factors, research studies, and technical details

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    218
    +0.13
    0.6%
    481
    +0.12
    0.6%
    277
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    516
    +0.13
    0.07
    51
    +0.12
    0.08
    288
    +0.11
    0.13
    Negative Logits
    nai
    -0.74
    assies
    -0.70
    ilet
    -0.68
    without
    -0.68
    achelor
    -0.68
    ardless
    -0.67
    emale
    -0.67
    licts
    -0.66
    ropolis
    -0.65
    itutes
    -0.64
    POSITIVE LOGITS
     factors
    0.95
     circumstances
    0.87
     negligence
    0.86
     circumstance
    0.83
     whims
    0.82
     constraints
    0.79
     ingenuity
    0.78
     incompetence
    0.77
     intuition
    0.77
     combination
    0.77
    Activations Density 2.860%

    No Known Activations