© 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. 15830
    Prev
    Next
    INDEX
    Explanations

    words related to travel and historical movements

    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
    136
    +0.10
    0.5%
    183
    +0.10
    0.5%
    81
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    541
    +0.10
    0.06
    217
    +0.10
    0.04
    580
    +0.09
    0.05
    Negative Logits
    enos
    -0.68
    Forest
    -0.66
    larg
    -0.59
    eah
    -0.59
    SPONSORED
    -0.59
    otaur
    -0.59
    cess
    -0.58
     Simulator
    -0.55
    owitz
    -0.54
    adra
    -0.54
    POSITIVE LOGITS
     aback
    1.04
     by
    1.04
    own
    0.79
     BY
    0.79
    bys
    0.77
     Parenthood
    0.73
    inel
    0.71
    eals
    0.71
    entious
    0.71
     thereto
    0.70
    Activations Density 0.441%

    No Known Activations