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 3072
    5. 8-RES_FS3072-JB
    6. 2537
    Prev
    Next
    INDEX
    Explanations

    phrases related to policy and societal issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    36
    +0.25
    1.2%
    393
    +0.16
    0.8%
    362
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.25
    0.22
    436
    +0.16
    0.09
    393
    +0.12
    0.10
    Negative Logits
    Versions
    -0.88
    Edit
    -0.84
    effects
    -0.80
    AIDS
    -0.76
    uin
    -0.76
    units
    -0.75
    agues
    -0.74
    Effects
    -0.73
    enery
    -0.72
    Links
    -0.69
    POSITIVE LOGITS
     reminder
    1.20
     lot
    1.19
     huge
    1.13
     fascinating
    1.12
     testament
    1.10
     HUGE
    1.08
     tad
    1.07
     bit
    1.06
     continuation
    1.06
     reflection
    1.02
    Activations Density 0.769%

    No Known Activations