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. 46165
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "single parents"

    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
    336
    +0.11
    0.5%
    269
    +0.10
    0.4%
    302
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.01
    284
    +0.10
    0.01
    343
    +0.09
    0.01
    Negative Logits
    inosaur
    -0.84
    itude
    -0.67
     skelet
    -0.65
    ns
    -0.64
    nikov
    -0.64
     therap
    -0.62
    some
    -0.61
    ividual
    -0.58
    sylvania
    -0.58
    aline
    -0.57
    POSITIVE LOGITS
    isine
    0.97
    ÃŁ
    0.94
    seless
    0.94
    pta
    0.93
    owa
    0.91
    ples
    0.90
    selage
    0.88
    hei
    0.88
    qq
    0.86
    utenant
    0.86
    Activations Density 0.005%

    No Known Activations