© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 18638
    Prev
    Next
    INDEX
    Explanations

    proper names of people or entities

    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
    321
    +0.13
    0.6%
    735
    +0.13
    0.6%
    373
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.04
    735
    +0.13
    0.02
    511
    +0.12
    0.02
    Negative Logits
     Laos
    -0.70
    á¹
    -0.66
    irlf
    -0.65
     Proposition
    -0.63
    ãĥŁ
    -0.61
    ruary
    -0.61
    Tea
    -0.61
     Guinea
    -0.59
     Nicaragua
    -0.59
    issance
    -0.58
    POSITIVE LOGITS
    antage
    0.72
    elson
    0.70
    arkin
    0.67
    owitz
    0.65
    iel
    0.63
    kowski
    0.63
    edin
    0.62
    taker
    0.61
    elsen
    0.60
    agu
    0.60
    Activations Density 0.054%

    No Known Activations