© 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. 18432
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives related to investigative activities

    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
    1
    +0.10
    0.4%
    339
    +0.10
    0.4%
    328
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.10
    0.05
    453
    +0.10
    0.04
    288
    +0.10
    0.05
    Negative Logits
    anders
    -0.80
    APH
    -0.73
    ulhu
    -0.70
    REL
    -0.69
    ploma
    -0.69
    adr
    -0.67
    aden
    -0.67
    conservancy
    -0.66
    agine
    -0.64
    ADS
    -0.64
    POSITIVE LOGITS
    ly
    3.18
    LY
    2.08
    fully
    1.40
    lys
    1.40
    liness
    1.37
    lies
    1.32
    edly
    1.27
    ELY
    1.27
    ously
    1.25
    ity
    1.19
    Activations Density 0.190%

    No Known Activations