© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 1536
    9. 8-RES_FS1536-JB
    11. 1094
    Prev
    Next
    INDEX
    Explanations

    phrases related to lists or names of people

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    501
    +0.12
    0.5%
    285
    +0.10
    0.5%
    380
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.10
    232
    +0.10
    0.09
    288
    +0.10
    0.13
    Negative Logits
    ly
    -0.91
     Gork
    -0.69
    Bloomberg
    -0.69
    BOOK
    -0.67
    liest
    -0.65
    LY
    -0.64
    lished
    -0.63
    lled
    -0.63
    lda
    -0.62
    REM
    -0.61
    POSITIVE LOGITS
    iard
    1.44
    uminati
    1.32
    oyd
    1.18
    iday
    1.16
    enium
    1.13
    aday
    1.10
    ibrary
    1.07
    ounge
    1.07
    ipop
    1.06
    inois
    1.05
    Activations Density 2.549%

    No Known Activations