© 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. 23036
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences containing the expression "In a nutshell" or similar variations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that summarize information or provide definitions

    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
    20439
    -0.90
    psey
    -0.75
    inel
    -0.71
    olith
    -0.69
     unwitting
    -0.68
    avorite
    -0.68
     sweats
    -0.65
    him
    -0.64
    assic
    -0.64
    cler
    -0.63
    POSITIVE LOGITS
     nutshell
    1.04
     Definitions
    0.85
     gist
    0.84
     Meaning
    0.78
    quote
    0.68
     outline
    0.68
     revolves
    0.68
    rss
    0.66
     boils
    0.66
     Overview
    0.66
    Activations Density 0.110%

    No Known Activations