© 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. 21571
    Prev
    Next
    INDEX
    Explanations

    phrases related to categorization or classification

    oai_token-act-pair · gpt-3.5-turbo

    references to categories and classifications

    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
    eeds
    -0.67
     advances
    -0.65
    displayText
    -0.61
     nipples
    -0.60
    facts
    -0.59
     noises
    -0.57
    released
    -0.57
     visits
    -0.56
     taped
    -0.56
     reconnect
    -0.56
    POSITIVE LOGITS
     category
    1.90
     categories
    1.51
    ategory
    1.37
    category
    1.35
     bracket
    1.19
     tier
    1.14
     Category
    1.08
     grouping
    1.08
     Categories
    1.06
     group
    1.05
    Activations Density 0.397%

    No Known Activations