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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 506
    Prev
    Next
    INDEX
    Explanations

    names and title-like terms in various contexts, potentially related to social media or activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    378
    +0.16
    0.8%
    570
    +0.12
    0.5%
    430
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    570
    +0.16
    0.03
    130
    +0.12
    0.06
    667
    +0.11
    0.07
    Negative Logits
    20439
    -0.69
    omorphic
    -0.68
    hom
    -0.65
    Hom
    -0.60
    icum
    -0.57
    dogs
    -0.56
    brid
    -0.56
     bom
    -0.55
     cheek
    -0.55
     nar
    -0.54
    POSITIVE LOGITS
    ribute
    0.66
    ]);
    0.66
    Merit
    0.63
    ãħĭ
    0.62
     SetFontSize
    0.61
    isoft
    0.61
    ?????-
    0.60
     ±
    0.60
    %%%%
    0.59
    ¼
    0.59
    Activations Density 2.165%

    No Known Activations