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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 1502
    Prev
    Next
    INDEX
    Explanations

    the word "os" and variations of it

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    622
    +0.11
    0.5%
    767
    +0.10
    0.5%
    649
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    767
    +0.11
    0.03
    511
    +0.10
    0.03
    622
    +0.10
    0.02
    Negative Logits
    ãĤ¡
    -0.71
    rence
    -0.66
    bler
    -0.65
    taker
    -0.64
    OWS
    -0.63
    ASED
    -0.63
    BRE
    -0.62
    OUT
    -0.61
    ufact
    -0.60
    TextColor
    -0.59
    POSITIVE LOGITS
    hiba
    1.46
    heet
    1.24
    ophical
    1.19
    keleton
    1.11
    leep
    1.07
    omething
    1.06
    aurus
    1.06
    opher
    1.05
    ocial
    1.04
    mith
    1.04
    Activations Density 0.040%

    No Known Activations