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 1536
    5. 8-RES_FS1536-JB
    6. 371
    Prev
    Next
    INDEX
    Explanations

    information related to news articles and current events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    373
    +0.24
    1.2%
    430
    +0.12
    0.6%
    350
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.24
    -0.03
    530
    +0.12
    0.10
    430
    +0.09
    0.10
    Negative Logits
    username
    -0.72
    uds
    -0.61
    course
    -0.60
    cation
    -0.59
    orr
    -0.58
     assum
    -0.58
    opter
    -0.57
    kat
    -0.56
    lished
    -0.55
     Exhibition
    -0.55
    POSITIVE LOGITS
    WASHINGTON
    0.81
    LIN
    0.71
     COUNTY
    0.71
     POL
    0.71
    SHARE
    0.70
     CITY
    0.70
    ccording
    0.67
     JUL
    0.67
    MEN
    0.67
    )--
    0.65
    Activations Density 1.675%

    No Known Activations