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. 23827
    Prev
    Next
    INDEX
    Explanations

    references to faculty and staff within educational contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    288
    +0.14
    0.6%
    71
    +0.12
    0.5%
    285
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    325
    +0.14
    0.01
    288
    +0.12
    0.01
    285
    +0.11
    0.01
    Negative Logits
     launchers
    -0.68
    tar
    -0.67
     launcher
    -0.66
    nings
    -0.65
    6666
    -0.64
    lar
    -0.61
     Zimbabwe
    -0.61
     GPS
    -0.60
     HERO
    -0.60
     Rossi
    -0.60
    POSITIVE LOGITS
     faculty
    1.01
     members
    0.99
    ulty
    0.98
     member
    0.97
    members
    0.95
    llor
    0.94
    member
    0.91
     senate
    0.90
     unions
    0.83
     Members
    0.81
    Activations Density 0.018%

    No Known Activations