© 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. 12-RES-JB
    11. 3965
    Prev
    Next
    INDEX
    Explanations

    sneezing-related actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of the word "sneak" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     circumstance
    -0.69
    ĺħ
    -0.65
     Parenthood
    -0.65
     Globe
    -0.65
     Belt
    -0.65
     bases
    -0.64
     Places
    -0.63
     myths
    -0.62
     Basin
    -0.62
     circumstances
    -0.62
    POSITIVE LOGITS
    ez
    1.78
    aker
    1.68
    akers
    1.45
    aks
    1.41
    aky
    1.39
    ering
    1.37
    aked
    1.37
    aking
    1.28
    eker
    1.20
    ered
    1.12
    Activations Density 0.049%

    No Known Activations