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. 541
    Prev
    Next
    INDEX
    Explanations

    phrases related to fundraising, events, and details about specific plans or projects

    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
    655
    +0.12
    0.5%
    423
    +0.10
    0.5%
    437
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    655
    +0.12
    0.11
    609
    +0.10
    0.09
    77
    +0.09
    0.07
    Negative Logits
     ([
    -0.73
    otonin
    -0.65
    farious
    -0.62
    reetings
    -0.59
    },{"
    -0.58
    ocy
    -0.58
    renches
    -0.58
    onomy
    -0.58
     [-
    -0.57
    ottesville
    -0.57
    POSITIVE LOGITS
     notwithstanding
    0.91
    nown
    0.89
    arently
    0.84
     euphem
    0.78
     incidentally
    0.77
    pecially
    0.76
     preferring
    0.74
    which
    0.74
     equivalent
    0.73
     preferably
    0.73
    Activations Density 3.853%

    No Known Activations