© 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. 11978
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific individual named "Am" and numerical values after the name

    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
    616
    +0.10
    0.5%
    18
    +0.10
    0.5%
    145
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    18
    +0.10
    0.03
    676
    +0.10
    0.03
    145
    +0.10
    0.02
    Negative Logits
     diving
    -0.71
     directions
    -0.68
     wart
    -0.68
    EStreamFrame
    -0.68
     concession
    -0.68
    ãģį
    -0.67
     aver
    -0.65
     learners
    -0.64
    vous
    -0.63
     flair
    -0.62
    POSITIVE LOGITS
    ethyst
    1.33
    bitious
    1.28
    sterdam
    1.20
    endment
    1.17
    ulet
    1.16
    nesia
    1.16
    nesty
    1.09
    ateurs
    1.05
    ateur
    1.04
    azon
    1.03
    Activations Density 0.016%

    No Known Activations