© 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. 5331
    Prev
    Next
    INDEX
    Explanations

    words related to sensationalism and storytelling

    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
    314
    +0.12
    0.5%
    472
    +0.10
    0.4%
    343
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.05
    116
    +0.10
    0.02
    409
    +0.09
    0.02
    Negative Logits
     Caesar
    -0.67
    poon
    -0.63
    kens
    -0.62
     Armored
    -0.62
    ————
    -0.61
     Thor
    -0.59
    mosp
    -0.59
    cone
    -0.58
    lihood
    -0.55
     DRAG
    -0.55
    POSITIVE LOGITS
    ists
    2.49
    ism
    2.48
    ist
    2.47
    istic
    2.32
    istically
    2.15
    isms
    1.78
    ary
    1.71
    istical
    1.70
    ISM
    1.63
    IST
    1.60
    Activations Density 0.130%

    No Known Activations