© 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. 19659
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "mere" with high activation values

    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
    99
    +0.12
    0.6%
    498
    +0.12
    0.5%
    616
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    498
    +0.12
    0.02
    99
    +0.12
    0.02
    106
    +0.11
    0.02
    Negative Logits
     Also
    -0.64
    illas
    -0.63
     Locked
    -0.63
     destro
    -0.63
     smartest
    -0.62
    anwhile
    -0.61
     accordingly
    -0.61
    leneck
    -0.61
     extensively
    -0.61
    multipl
    -0.60
    POSITIVE LOGITS
     mortals
    1.30
    ifiable
    0.82
     superficial
    0.78
     incidental
    0.77
     curs
    0.77
     curiosity
    0.77
    ton
    0.76
     mortal
    0.75
     coincidence
    0.74
     consolation
    0.72
    Activations Density 0.027%

    No Known Activations