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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 1225
    Prev
    Next
    INDEX
    Explanations

    color codes and patterns

    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
    373
    +0.12
    0.5%
    297
    +0.10
    0.4%
    702
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.12
    0.08
    373
    +0.10
    -0.05
    640
    +0.09
    0.09
    Negative Logits
    76561
    -0.76
     Sapp
    -0.70
     reconc
    -0.68
    scrib
    -0.68
    ktop
    -0.64
    lycer
    -0.63
     Clarks
    -0.62
     Pric
    -0.62
    eph
    -0.60
     Appl
    -0.60
    POSITIVE LOGITS
    III
    0.89
    ¾
    0.84
    Secondly
    0.84
     secondly
    0.84
    VII
    0.83
    II
    0.83
    ii
    0.83
    iii
    0.80
    2
    0.79
    γ
    0.75
    Activations Density 1.436%

    No Known Activations