© 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. 9443
    Prev
    Next
    INDEX
    Explanations

    references to someone or something named "Rose"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Rose," possibly indicating a focus on a character, place, or concept associated with that name

    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
    SPONSORED
    -0.73
    essions
    -0.62
    ities
    -0.58
     illiter
    -0.58
    iazep
    -0.58
    SIGN
    -0.57
     midterm
    -0.57
     glutamate
    -0.55
     Bulgarian
    -0.55
     gist
    -0.55
    POSITIVE LOGITS
    mary
    1.69
    anne
    1.26
    mont
    1.20
    bery
    1.16
    velt
    1.10
    xual
    1.09
    water
    1.04
    hill
    1.01
    mond
    1.00
    wood
    1.00
    Activations Density 0.034%

    No Known Activations