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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 999
    Prev
    Next
    INDEX
    Explanations

    descriptions of political events and movements

    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
    481
    +0.17
    0.8%
    139
    +0.13
    0.6%
    393
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.17
    0.09
    561
    +0.13
    0.09
    368
    +0.11
    0.09
    Negative Logits
    ãĥ¥
    -0.71
    worldly
    -0.70
    Russ
    -0.63
    âĶĢâĶĢâĶĢâĶĢ
    -0.60
    zn
    -0.59
    ARY
    -0.59
    Interested
    -0.59
    ize
    -0.58
    ARCH
    -0.58
    Apps
    -0.58
    POSITIVE LOGITS
     joins
    0.90
     withdrew
    0.82
     denies
    0.82
     welcomed
    0.79
     wrote
    0.77
     was
    0.77
     teaches
    0.77
     welcomes
    0.77
     greets
    0.76
     urged
    0.76
    Activations Density 1.364%

    No Known Activations