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. 26034
    Prev
    Next
    INDEX
    Explanations

    numerical ratings related to evaluations or assessments

    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
    274
    +0.13
    0.6%
    127
    +0.11
    0.5%
    575
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.13
    0.02
    225
    +0.11
    0.01
    540
    +0.10
    0.01
    Negative Logits
    adr
    -0.87
     Alz
    -0.77
    ansson
    -0.77
    ilus
    -0.76
    prus
    -0.75
    ocrates
    -0.69
    ĸļ
    -0.68
    cling
    -0.67
    stasy
    -0.67
    xon
    -0.67
    POSITIVE LOGITS
     rating
    1.09
     ratings
    1.03
     Ratings
    0.96
    âĺħâĺħ
    0.91
    Rating
    0.89
     Rating
    0.87
    Reviewer
    0.86
    Beer
    0.80
     downgrade
    0.78
    card
    0.78
    Activations Density 0.009%

    No Known Activations