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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 8404
    Prev
    Next
    INDEX
    Explanations

    information related to graduates, their openness to new experiences, and their potential ability to contribute effectively

    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
    481
    +0.13
    0.6%
    218
    +0.12
    0.5%
    761
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    60
    +0.13
    0.04
    139
    +0.12
    0.04
    761
    +0.11
    0.04
    Negative Logits
    NetMessage
    -0.71
     fined
    -0.66
    anus
    -0.66
     Manufact
    -0.65
    avis
    -0.62
    lag
    -0.61
     allowance
    -0.61
     Stores
    -0.61
    Cooldown
    -0.61
     Copyright
    -0.60
    POSITIVE LOGITS
     expertise
    1.06
     articulate
    1.03
     talents
    0.98
     qualities
    0.95
     credible
    0.94
     excellence
    0.93
     compet
    0.92
     charisma
    0.90
     talent
    0.90
     suitable
    0.89
    Activations Density 0.393%

    No Known Activations