© 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. 21037
    Prev
    Next
    INDEX
    Explanations

    film or TV show titles followed by a year in parentheses

    oai_token-act-pair · gpt-3.5-turbo

    opening parentheses in various contexts

    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
     spir
    -0.73
     impact
    -0.71
     upon
    -0.71
     appreci
    -0.70
     funnel
    -0.70
     impeachment
    -0.70
     [âĢ¦]
    -0.69
     disg
    -0.69
     perme
    -0.68
     smugg
    -0.67
    POSITIVE LOGITS
    formerly
    1.49
    includes
    1.40
    feat
    1.34
    optional
    1.34
    aka
    1.32
    2007
    1.30
    2011
    1.29
    2006
    1.28
    2003
    1.28
    1996
    1.28
    Activations Density 0.148%

    No Known Activations