© 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. 7-RES-JB
    11. 21716
    Prev
    Next
    INDEX
    Explanations

    mentions of numeric quantities or lists of items

    oai_token-act-pair · gpt-3.5-turbo

    references to a repeated phrase or idea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.80
    ipedia
    -0.75
    Depth
    -0.73
    ared
    -0.73
    hest
    -0.71
    =]
    -0.71
    asion
    -0.71
    atown
    -0.69
    ario
    -0.68
    opus
    -0.68
    POSITIVE LOGITS
     factors
    1.05
     occasions
    1.01
     ways
    0.97
     unanswered
    0.97
     reasons
    0.95
     aspects
    0.90
     different
    0.90
     variables
    0.88
     hundred
    0.87
     ailments
    0.87
    Activations Density 0.066%

    No Known Activations