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. 847
    Prev
    Next
    INDEX
    Explanations

    numbers with specific associations, possibly related to financial transactions or statistics

    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
    2
    +0.11
    0.5%
    285
    +0.10
    0.5%
    189
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.12
    343
    +0.10
    0.07
    220
    +0.10
    0.07
    Negative Logits
    swick
    -1.01
    xual
    -0.86
    eers
    -0.71
    eer
    -0.70
    urally
    -0.69
    resp
    -0.69
    uve
    -0.67
    elia
    -0.67
    arre
    -0.67
    efeated
    -0.67
    POSITIVE LOGITS
    Thirty
    1.01
    iam
    0.79
     ILCS
    0.78
    uate
    0.75
    678
    0.68
    izont
    0.68
    tein
    0.67
    uating
    0.67
    riers
    0.66
    anging
    0.66
    Activations Density 2.549%

    No Known Activations