© 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. 3-RES-JB
    11. 23359
    Prev
    Next
    INDEX
    Explanations

    keywords related to community events and interactions

    oai_token-act-pair · gpt-3.5-turbo

    references to community events and organizational activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Journal
    -0.79
    SOURCE
    -0.74
    )",
    -0.68
     Ibid
    -0.67
    byn
    -0.67
     DOI
    -0.66
     constitu
    -0.66
     photoc
    -0.65
    CHQ
    -0.64
     UNCLASSIFIED
    -0.63
    POSITIVE LOGITS
    juries
    0.80
     matchup
    0.70
     render
    0.70
     bolted
    0.70
     offseason
    0.67
     SPORTS
    0.67
    gdala
    0.66
    jured
    0.65
     ankle
    0.65
    ESPN
    0.65
    Activations Density 1.306%

    No Known Activations