© 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. 21230
    Prev
    Next
    INDEX
    Explanations

    historical and biographical information about notable figures and locations

    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
    +0.18
    0.8%
    373
    +0.13
    0.6%
    160
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    702
    +0.18
    0.03
    112
    +0.13
    0.03
    160
    +0.12
    0.03
    Negative Logits
    wagen
    -0.90
     reinvest
    -0.66
     assured
    -0.65
    nesday
    -0.65
     goose
    -0.64
     tomorrow
    -0.63
     pens
    -0.62
     rooft
    -0.62
     bands
    -0.61
     diminishing
    -0.61
    POSITIVE LOGITS
     edit
    1.65
    ?]
    1.37
    actionDate
    1.07
    !]
    1.01
     ]
    1.00
    edit
    0.99
     Edit
    0.97
    src
    0.97
    ËĪ
    0.96
    emphasis
    0.95
    Activations Density 0.018%

    No Known Activations