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. 571
    Prev
    Next
    INDEX
    Explanations

    statements related to legal matters and public policy

    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
    38
    +0.10
    0.4%
    640
    +0.10
    0.4%
    719
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.10
    0.14
    719
    +0.10
    0.13
    426
    +0.09
    0.11
    Negative Logits
     Belg
    -0.82
     confinement
    -0.71
     bast
    -0.71
     machine
    -0.71
     shack
    -0.68
     dispers
    -0.67
     range
    -0.67
     dirt
    -0.66
     buggy
    -0.66
     assemb
    -0.66
    POSITIVE LOGITS
    ª
    1.33
    ¹
    1.31
    Į
    1.22
    º
    1.21
    ¤
    1.20
    į
    1.20
    Ń
    1.18
    £
    1.15
    ľ
    1.13
    ł
    1.13
    Activations Density 0.749%

    No Known Activations