© 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 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. 9-RES-JB
    11. 4687
    Prev
    Next
    INDEX
    Explanations

    dairy products and ingredients commonly used in cooking

    oai_token-act-pair · gpt-3.5-turbo

    instances of a special token indicating the end of the content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     seism
    -0.88
     Gamergate
    -0.79
     DPR
    -0.69
     Intelligent
    -0.68
     dispatch
    -0.68
     Sent
    -0.68
     SIG
    -0.67
     seismic
    -0.67
     autonomous
    -0.67
     billing
    -0.67
    POSITIVE LOGITS
    iflower
    1.14
    berries
    1.10
     spices
    1.09
    innamon
    1.08
    onut
    1.07
    amel
    1.07
    atmeal
    1.06
     vinegar
    1.05
    ilantro
    1.05
    fruit
    1.05
    Activations Density 0.214%

    No Known Activations