© 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. 7550
    Prev
    Next
    INDEX
    Explanations

    names related to a specific character, Lex Luthor, as well as mentions of specific locations or events related to Lex Luthor

    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
    323
    +0.11
    0.5%
    356
    +0.10
    0.5%
    525
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    525
    +0.11
    0.01
    699
    +0.10
    0.01
    1
    +0.10
    0.01
    Negative Logits
     extremes
    -0.70
    ailable
    -0.69
    OTS
    -0.69
    llah
    -0.67
    ============
    -0.66
    ONEY
    -0.66
    Ø©
    -0.66
    quartered
    -0.64
    orld
    -0.63
     parties
    -0.63
    POSITIVE LOGITS
     Luthor
    1.31
     Machina
    1.14
    icon
    1.05
    icians
    0.99
    ical
    0.94
    iom
    0.93
     Lug
    0.89
    esis
    0.88
    sey
    0.87
    avier
    0.86
    Activations Density 0.027%

    No Known Activations