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. 500
    Prev
    Next
    INDEX
    Explanations

    entities related to global events or competitions

    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
    118
    +0.12
    0.5%
    483
    +0.11
    0.5%
    42
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.12
    -0.06
    284
    +0.11
    0.10
    314
    +0.10
    0.00
    Negative Logits
     impulse
    -0.62
    ¯
    -0.61
    hoff
    -0.60
    ovych
    -0.60
    yip
    -0.59
     Feast
    -0.59
     reckoning
    -0.58
     Shutterstock
    -0.57
    idays
    -0.56
    XM
    -0.55
    POSITIVE LOGITS
    ulhu
    0.94
    å°Ĩ
    0.81
    estial
    0.81
    igham
    0.77
    rency
    0.76
    ãĤ¼ãĤ¦ãĤ¹
    0.76
    berus
    0.76
    cled
    0.75
    ioxide
    0.74
    bral
    0.74
    Activations Density 2.643%

    No Known Activations