© 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. 17530
    Prev
    Next
    INDEX
    Explanations

    phrases related to global issues and society

    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
    447
    +0.22
    1.0%
    672
    +0.11
    0.5%
    636
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.22
    0.07
    672
    +0.11
    0.04
    202
    +0.11
    0.04
    Negative Logits
     Siri
    -0.63
    å¦
    -0.61
     consolation
    -0.60
    REDACTED
    -0.58
    autions
    -0.56
     Fet
    -0.56
    kHz
    -0.55
     pestic
    -0.54
     persuasion
    -0.53
    »Ĵ
    -0.53
    POSITIVE LOGITS
     anew
    0.86
     ASAP
    0.86
    selves
    0.85
    's
    0.84
     accordingly
    0.83
     economically
    0.81
     prematurely
    0.76
     financially
    0.76
     vertically
    0.75
     indefinitely
    0.73
    Activations Density 0.365%

    No Known Activations