© 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 EvalsExportsinterp-engineNEWAPI 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. 14420
    Prev
    Next
    INDEX
    Explanations

    repetitive sequences of tokens ending with a symbol, seemingly related to a specific type of text or code

    oai_token-act-pair · gpt-3.5-turbo

    frequently occurring phrases or repeated elements in the text

    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
     eleph
    -1.10
     pione
    -1.03
     oun
    -0.88
     subur
    -0.88
     complementary
    -0.87
     brid
    -0.87
     carbohyd
    -0.87
     earthqu
    -0.84
    ¥ŀ
    -0.84
     exting
    -0.83
    POSITIVE LOGITS
    Yeah
    1.80
    Seriously
    1.78
    Fuck
    1.75
    And
    1.75
    Yep
    1.74
    Oh
    1.73
    Cause
    1.73
    Maybe
    1.71
    Looks
    1.67
    You
    1.66
    Activations Density 0.360%

    No Known Activations