Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 23904
    Prev
    Next
    INDEX
    Explanations

    references to the name "Wy" and its variants, indicating a focus on people or subjects associated with that name

    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
    99
    +0.19
    0.9%
    240
    +0.16
    0.7%
    68
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.19
    0.01
    240
    +0.16
    0.01
    659
    +0.10
    0.01
    Negative Logits
    inates
    -0.79
    ãĥ¼ãĥĨ
    -0.72
    DERR
    -0.71
     Lauder
    -0.70
    å§«
    -0.69
    ividual
    -0.68
    raints
    -0.67
    imately
    -0.65
    IUM
    -0.64
    ÙĴ
    -0.64
    POSITIVE LOGITS
    atts
    1.15
    tch
    1.14
    vern
    1.06
    combe
    1.04
    cz
    1.02
    nton
    1.01
    lde
    0.98
    nec
    0.96
    ank
    0.95
    nda
    0.92
    Activations Density 0.008%

    No Known Activations