© 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. 7559
    Prev
    Next
    INDEX
    Explanations

    triggers related to exclamations and emotional expressions

    oai_token-act-pair · gpt-3.5-turbo

    repeated characters or sequences that indicate a formatting or encoding issue

    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
     Shant
    -0.70
     Tid
    -0.70
     photoc
    -0.69
     mete
    -0.67
     Shap
    -0.65
     seiz
    -0.64
     Xan
    -0.64
     horizont
    -0.63
     Synd
    -0.63
     Drawn
    -0.61
    POSITIVE LOGITS
    ķ
    1.15
    «
    1.11
    Ŀ
    1.06
    Ĵ
    1.04
    Ń
    1.04
    ĸ
    1.03
    ¬
    1.03
    ´
    1.03
    ĵ
    1.02
    ª
    1.02
    Activations Density 0.118%

    No Known Activations