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 49152
    5. 8-RES_FS49152-JB
    6. 43211
    Prev
    Next
    INDEX
    Explanations

    specific names and organizations related to legal and political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    447
    +0.23
    1.0%
    481
    +0.17
    0.8%
    294
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.23
    0.05
    288
    +0.17
    0.06
    481
    +0.10
    0.06
    Negative Logits
    ãĤ´ãĥ³
    -0.68
    odox
    -0.65
    $.
    -0.62
    utterstock
    -0.62
    BUT
    -0.58
    ËĪ
    -0.54
    Aug
    -0.54
    Ĭ±
    -0.54
     ):
    -0.53
    +.
    -0.51
    POSITIVE LOGITS
    %"
    1.18
    .")
    1.08
    "
    1.07
    ,"
    1.05
    !"
    1.04
    ")
    1.03
    ").
    1.03
     ..."
    1.02
     cannot
    1.01
    ?"
    1.00
    Activations Density 0.333%

    No Known Activations