© 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. 14189
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "fast" followed by a hyphen and a word related to speed or growth

    oai_token-act-pair · gpt-3.5-turbo

    references to rapid or fast-paced developments or changes

    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
     merits
    -0.74
     reservations
    -0.70
     Ivy
    -0.67
     DOI
    -0.66
     GHC
    -0.66
     quotas
    -0.65
     context
    -0.65
     ceiling
    -0.64
     Bild
    -0.63
     Cree
    -0.63
    POSITIVE LOGITS
    moving
    1.58
    paced
    1.56
    growing
    1.47
    twitch
    1.28
    rising
    1.28
    changing
    1.25
    food
    1.23
    talking
    1.21
    acting
    1.21
    travel
    1.21
    Activations Density 0.029%

    No Known Activations