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. 46090
    Prev
    Next
    INDEX
    Explanations

    the phrase "of" in various contexts, indicating a focus on parts or sections within a document

    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
    393
    +0.10
    0.5%
    43
    +0.09
    0.4%
    572
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    557
    +0.10
    0.02
    296
    +0.09
    0.03
    680
    +0.09
    0.02
    Negative Logits
    ateurs
    -0.75
    respective
    -0.71
    opp
    -0.66
     disproportionately
    -0.66
     favoured
    -0.65
    soever
    -0.64
    MpServer
    -0.61
     idols
    -0.61
    arers
    -0.61
     wizards
    -0.61
    POSITIVE LOGITS
     ARTICLE
    0.96
     article
    0.92
     Conversation
    0.85
     VIDEOS
    0.84
     excerpt
    0.84
     HuffPost
    0.82
     FAQ
    0.79
     interview
    0.79
     Interview
    0.79
    FAQ
    0.78
    Activations Density 0.073%

    No Known Activations