© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 24417
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific term or company named "Silver"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "silver."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etically
    -0.95
    NEY
    -0.75
    etic
    -0.72
     Gutenberg
    -0.70
    lov
    -0.69
    esy
    -0.68
    etics
    -0.67
    ynt
    -0.65
    inen
    -0.63
    ========
    -0.60
    POSITIVE LOGITS
     iod
    1.12
    ware
    1.11
     lining
    1.02
    mine
    0.91
    moon
    0.90
    mont
    0.90
    stein
    0.89
    anguage
    0.87
     medal
    0.87
    blind
    0.84
    Activations Density 0.028%

    No Known Activations