© 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 EvalsExportsAPI 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. 7891
    Prev
    Next
    INDEX
    Explanations

    economic and geopolitical terms and concepts

    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
    87
    +0.39
    2.1%
    447
    +0.14
    0.7%
    157
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.39
    -0.01
    665
    +0.14
    0.09
    157
    +0.12
    0.07
    Negative Logits
    die
    -0.66
     boobs
    -0.59
    Bey
    -0.56
     capt
    -0.54
     died
    -0.54
     lyrics
    -0.54
     Died
    -0.53
    !/
    -0.53
     Dude
    -0.53
     thereof
    -0.53
    POSITIVE LOGITS
     backlog
    0.68
     hiring
    0.68
     enforcing
    0.66
     subsid
    0.65
     aggressively
    0.65
     arming
    0.65
     issuing
    0.65
     contingency
    0.64
     stringent
    0.64
     policies
    0.63
    Activations Density 0.768%

    No Known Activations