© 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. 4-RES-JB
    11. 10683
    Prev
    Next
    INDEX
    Explanations

    references to scientific concepts, technical terms, and academic disciplines

    oai_token-act-pair · gpt-3.5-turbo

    terms related to health, medicine, and the scientific study of substances or diseases

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

    No Comments

    Negative Logits
     âĢº
    -0.51
    oba
    -0.51
    OOOO
    -0.49
    _-_
    -0.46
     Morty
    -0.46
    nos
    -0.46
     Bod
    -0.44
    reek
    -0.44
    raw
    -0.44
    ived
    -0.42
    POSITIVE LOGITS
     Citadel
    0.55
    worthiness
    0.53
    '."
    0.53
     phenotype
    0.50
     initiation
    0.49
    folio
    0.48
     portfolio
    0.48
    eers
    0.47
     workforce
    0.47
     toile
    0.46
    Activations Density 1.284%

    No Known Activations