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. 21845
    Prev
    Next
    INDEX
    Explanations

    names related to a specific person

    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
    374
    +0.12
    0.5%
    313
    +0.11
    0.5%
    311
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    374
    +0.12
    0.01
    326
    +0.11
    0.01
    313
    +0.10
    0.01
    Negative Logits
    ickr
    -0.82
    ctica
    -0.79
    apping
    -0.72
    ograph
    -0.69
    payers
    -0.69
    ographer
    -0.69
    ography
    -0.68
    ographed
    -0.68
    cape
    -0.68
    ucc
    -0.67
    POSITIVE LOGITS
    glers
    0.91
    Hunt
    0.87
     Chavez
    0.84
    ged
    0.70
    inx
    0.70
     Hou
    0.66
    sty
    0.64
    mong
    0.63
    asus
    0.62
    adish
    0.61
    Activations Density 0.036%

    No Known Activations