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 6144
    5. 8-RES_FS6144-JB
    6. 5392
    Prev
    Next
    INDEX
    Explanations

    information related to various topics such as exceptional abilities, financial matters, international relations, legal rights, tax policies, social change, technological advancements, and border security

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    57
    +0.14
    0.6%
    288
    +0.09
    0.4%
    413
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.20
    57
    +0.09
    0.09
    575
    +0.09
    0.13
    Negative Logits
    )=(
    -0.70
    é¾įåĸļ士
    -0.65
    Phase
    -0.60
     Orig
    -0.57
     Procedure
    -0.57
    IBLE
    -0.56
     Canaver
    -0.56
    Dim
    -0.55
    upon
    -0.55
    agonist
    -0.54
    POSITIVE LOGITS
     etc
    0.88
     or
    0.84
    / 
    0.83
     and
    0.75
    ModLoader
    0.66
    /.
    0.64
     bombings
    0.61
     &
    0.60
    /
    0.60
     livest
    0.59
    Activations Density 2.300%

    No Known Activations