© 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. 5872
    Prev
    Next
    INDEX
    Explanations

    dates and events in a chronological sequence

    oai_token-act-pair · gpt-3.5-turbo

    historical references to events involving rebranding or changes in ownership

    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
     Conversation
    -0.78
     Quote
    -0.67
     harms
    -0.66
    DAY
    -0.63
     guessing
    -0.63
     unanswered
    -0.63
     suspense
    -0.62
     inacc
    -0.62
     Waiting
    -0.62
     Saying
    -0.61
    POSITIVE LOGITS
     renamed
    1.40
     expanded
    1.38
     relocated
    1.32
     merged
    1.32
     reformed
    1.22
     morphed
    1.19
     transitioned
    1.16
     revived
    1.14
     upgraded
    1.14
     replaced
    1.14
    Activations Density 0.308%

    No Known Activations