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 3072
    5. 8-RES_FS3072-JB
    6. 2531
    Prev
    Next
    INDEX
    Explanations

    terms related to team dynamics and team performance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    270
    +0.11
    0.5%
    260
    +0.09
    0.4%
    84
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    405
    +0.11
    0.07
    270
    +0.09
    0.04
    260
    +0.09
    0.07
    Negative Logits
    hesis
    -0.81
    OGR
    -0.79
    chnology
    -0.77
    quez
    -0.77
    rift
    -0.76
    SS
    -0.73
    SPONSORED
    -0.72
    ombat
    -0.71
    à¥
    -0.68
    cue
    -0.68
    POSITIVE LOGITS
     how
    0.92
     halfway
    0.84
     overcoming
    0.73
     preserving
    0.73
     reforming
    0.73
     getting
    0.73
     calib
    0.72
     protecting
    0.71
     improving
    0.71
     whether
    0.71
    Activations Density 0.471%

    No Known Activations