© 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. 11837
    Prev
    Next
    INDEX
    Explanations

    phrases indicating lists of items or ideas

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate lists or summaries of items or themes

    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
    endor
    -0.81
    avery
    -0.80
    byss
    -0.78
    etz
    -0.77
    iolet
    -0.76
    uca
    -0.76
    culosis
    -0.74
    ulhu
    -0.73
    rome
    -0.71
    ipient
    -0.70
    POSITIVE LOGITS
     examples
    1.45
     reasons
    1.21
     excerpts
    1.20
     highlights
    1.20
     salient
    1.18
     observations
    1.15
     suggestions
    1.15
     noteworthy
    1.12
     ways
    1.12
     notable
    1.11
    Activations Density 0.114%

    No Known Activations