© 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. 1-RES-JB
    11. 22236
    Prev
    Next
    INDEX
    Explanations

    words related to intense emotional reactions or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "tant" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     seeded
    -0.73
    ournals
    -0.70
    rounder
    -0.70
    endif
    -0.67
    side
    -0.64
    OLD
    -0.63
    edge
    -0.63
     Donation
    -0.62
     Patent
    -0.62
     endif
    -0.62
    POSITIVE LOGITS
     tant
    1.63
     Tant
    0.96
    amount
    0.93
    ority
    0.93
     reluct
    0.87
    alus
    0.86
    emonium
    0.85
    abase
    0.82
    rums
    0.80
     toile
    0.79
    Activations Density 0.008%

    No Known Activations