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. 26232
    Prev
    Next
    INDEX
    Explanations

    terms related to local geography, specifically coastal areas or features

    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
    526
    +0.16
    0.8%
    726
    +0.12
    0.6%
    170
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    147
    +0.16
    0.01
    726
    +0.12
    0.01
    170
    +0.12
    0.01
    Negative Logits
    plet
    -0.79
    ettings
    -0.78
    pton
    -0.77
    chy
    -0.76
    yip
    -0.71
    pared
    -0.70
    hov
    -0.70
    plets
    -0.68
    pload
    -0.67
     tiss
    -0.67
    POSITIVE LOGITS
    rophe
    1.31
    eful
    0.97
    rophic
    0.96
    ebook
    0.93
    efully
    0.88
    eele
    0.87
    rike
    0.86
    rian
    0.86
    anza
    0.85
    feeding
    0.84
    Activations Density 0.011%

    No Known Activations