© 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. 12-RES-JB
    11. 3556
    Prev
    Next
    INDEX
    Explanations

    conversations or dialogues in a narrative

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    quotations and punctuation related to dialogue or speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     satell
    -0.90
    ¥ŀ
    -0.81
     hemor
    -0.78
     challeng
    -0.77
     volunte
    -0.76
     millenn
    -0.75
     conflic
    -0.73
     tremend
    -0.73
     carbohyd
    -0.72
     tiss
    -0.66
    POSITIVE LOGITS
    Specifically
    0.50
     Specifically
    0.48
    âĢ
    0.47
    âĸ
    0.46
    ``
    0.45
    Newsletter
    0.45
    Additionally
    0.45
    png
    0.45
    âĻ¦
    0.45
    Enlarge
    0.44
    Activations Density 1.431%

    No Known Activations