© 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. 16729
    Prev
    Next
    INDEX
    Explanations

    geographical locations and specific terms related to government activities

    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
    373
    +0.18
    0.8%
    65
    +0.12
    0.5%
    689
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.09
    762
    +0.12
    0.09
    325
    +0.11
    0.07
    Negative Logits
    onom
    -0.66
    Sund
    -0.64
    alg
    -0.63
    Nar
    -0.61
     blu
    -0.61
     newcom
    -0.60
    yip
    -0.60
    IENT
    -0.59
    nar
    -0.59
    Lear
    -0.57
    POSITIVE LOGITS
     guiActiveUnfocused
    0.82
    places
    0.73
     violates
    0.67
     respectively
    0.65
     plus
    0.63
     yields
    0.61
    oids
    0.59
    hips
    0.59
     inciner
    0.58
     attest
    0.58
    Activations Density 0.599%

    No Known Activations