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. 1023
    Prev
    Next
    INDEX
    Explanations

    mentions of people's names ending with "mon"

    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
    444
    +0.11
    0.5%
    31
    +0.10
    0.5%
    174
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    444
    +0.11
    0.02
    174
    +0.10
    0.01
    31
    +0.10
    0.01
    Negative Logits
     Norn
    -0.70
    ACTED
    -0.66
     Paste
    -0.62
    ENG
    -0.61
    OHN
    -0.60
    î
    -0.60
    NRS
    -0.59
    EMP
    -0.59
     tomat
    -0.59
    RED
    -0.59
    POSITIVE LOGITS
    itored
    1.17
    etary
    1.10
    strous
    1.06
    ial
    1.05
    uclear
    1.01
    iac
    0.99
    ials
    0.96
    astery
    0.90
    ter
    0.87
    ious
    0.86
    Activations Density 0.021%

    No Known Activations