© 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. 6291
    Prev
    Next
    INDEX
    Explanations

    instances where something is being installed, attached, or applied

    oai_token-act-pair · gpt-3.5-turbo

    actions related to installation and setup processes

    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
    DATA
    -0.62
    ographical
    -0.57
    icipated
    -0.57
    Forest
    -0.54
    é¾įå
    -0.53
     Flavoring
    -0.52
     DRAG
    -0.52
    ographic
    -0.51
     ABE
    -0.51
    nel
    -0.51
    POSITIVE LOGITS
     therein
    0.83
     elsewhere
    0.77
     theirs
    0.77
     somewhere
    0.76
     haha
    0.76
     beforehand
    0.75
    abouts
    0.75
     nearby
    0.73
     ðŁĺ
    0.73
    own
    0.73
    Activations Density 0.232%

    No Known Activations