© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 1536
    9. 8-RES_FS1536-JB
    11. 90
    Prev
    Next
    INDEX
    Explanations

    the word "So" used as an introductory phrase or transitional word

    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
    240
    +0.12
    0.6%
    468
    +0.12
    0.5%
    55
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    240
    +0.12
    0.09
    55
    +0.12
    0.10
    559
    +0.11
    0.07
    Negative Logits
    theless
    -0.69
     Purg
    -0.63
     Halls
    -0.58
    ropolitan
    -0.54
    wreck
    -0.54
    work
    -0.54
     Scand
    -0.52
    rals
    -0.52
    works
    -0.52
     expectancy
    -0.52
    POSITIVE LOGITS
    bered
    1.37
    apy
    1.26
    oths
    1.25
    oner
    1.20
    othes
    1.16
    othe
    1.12
    ooo
    1.11
    oooo
    1.08
    aps
    1.02
     far
    1.00
    Activations Density 0.690%

    No Known Activations