© 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. 1-RES-JB
    11. 3501
    Prev
    Next
    INDEX
    Explanations

    references to the character "Sookie" and related terms such as "Cookie" and "bookmark."

    oai_token-act-pair · gpt-3.5-turbo

    references to cookies or cookie-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rait
    -0.69
    APE
    -0.64
    port
    -0.62
    romy
    -0.62
    APS
    -0.61
     erect
    -0.61
    anced
    -0.60
    ported
    -0.60
    inished
    -0.59
    rounded
    -0.58
    POSITIVE LOGITS
    ookie
    1.57
    leans
    0.92
    pedia
    0.90
    eties
    0.82
    edia
    0.82
     Dough
    0.80
    vier
    0.72
     Cookie
    0.69
    eers
    0.69
     Wire
    0.67
    Activations Density 0.015%

    No Known Activations