© 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. 7-RES-JB
    11. 23704
    Prev
    Next
    INDEX
    Explanations

    proper nouns containing the letter sequence "ck."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the sequence "ck"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exha
    -0.90
    psons
    -0.88
     livest
    -0.85
     Palestin
    -0.74
     helicop
    -0.73
    acco
    -0.71
     streng
    -0.71
     occas
    -0.70
    coni
    -0.70
    accompan
    -0.68
    POSITIVE LOGITS
    enstein
    1.10
    lace
    1.02
    erman
    1.01
    enzie
    1.00
    enger
    1.00
    hoff
    1.00
    etts
    0.97
    enberg
    0.94
    oning
    0.92
    crew
    0.91
    Activations Density 0.023%

    No Known Activations