© 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. 17537
    Prev
    Next
    INDEX
    Explanations

    instances where certain requirements or conditions need to be met in a document or record

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases involving keys and records in a data context

    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
    grim
    -0.73
    away
    -0.72
    Ħ¢
    -0.69
     Pace
    -0.69
    Uncommon
    -0.67
     Younger
    -0.65
     courageous
    -0.64
    catentry
    -0.63
    Pros
    -0.63
     Fol
    -0.62
    POSITIVE LOGITS
     correspond
    1.39
     contain
    1.33
     belong
    1.31
     reside
    1.19
     corresponds
    1.17
     behave
    1.16
     contains
    1.11
     overwrite
    1.11
     denote
    1.11
     inherit
    1.10
    Activations Density 0.213%

    No Known Activations