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

    Neuronpedia

    APICircuit 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. 1316
    Prev
    Next
    INDEX
    Explanations

    comparisons indicating superiority or inferiority

    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
    +0.11
    0.5%
    375
    +0.10
    0.4%
    183
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    655
    +0.11
    0.09
    539
    +0.10
    0.07
    183
    +0.10
    0.07
    Negative Logits
     largeDownload
    -0.72
    EMENT
    -0.69
    ãĥ´
    -0.68
    ilic
    -0.66
    ALE
    -0.66
    imity
    -0.66
    bilt
    -0.65
    OSP
    -0.64
    ALSE
    -0.63
    uto
    -0.63
    POSITIVE LOGITS
     usual
    0.95
     anything
    0.88
     anybody
    0.78
     anticipated
    0.76
     ever
    0.75
     anyone
    0.73
    average
    0.69
     expected
    0.68
     any
    0.68
    atos
    0.68
    Activations Density 0.914%

    No Known Activations