© 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 24576
    9. 8-RES_FS24576-JB
    11. 1400
    Prev
    Next
    INDEX
    Explanations

    names of individuals named Rosen

    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
    35
    +0.11
    0.5%
    99
    +0.10
    0.5%
    508
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.01
    316
    +0.10
    0.01
    547
    +0.10
    0.01
    Negative Logits
    į
    -0.85
    orsi
    -0.77
    ¥
    -0.69
     disadvant
    -0.66
    ³³³
    -0.65
     populous
    -0.64
     holidays
    -0.63
     Mecca
    -0.62
     Antar
    -0.62
     sizeable
    -0.61
    POSITIVE LOGITS
    feld
    1.40
    baum
    1.33
    wald
    1.20
    berg
    1.15
    quist
    1.15
    qv
    1.11
    bach
    1.09
    bard
    1.07
    enthal
    1.07
    stein
    1.07
    Activations Density 0.018%

    No Known Activations