© 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. 7518
    Prev
    Next
    INDEX
    Explanations

    mentions of literature

    oai_token-act-pair · gpt-3.5-turbo

    references to literature

    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
    fty
    -0.68
     twitch
    -0.66
    addafi
    -0.65
    por
    -0.64
     Maurit
    -0.62
    Bel
    -0.62
    adjust
    -0.61
     Gry
    -0.60
    ermanent
    -0.59
    oland
    -0.58
    POSITIVE LOGITS
     literature
    0.99
    istry
    0.77
    emis
    0.76
    DragonMagazine
    0.74
     Literature
    0.74
     laureate
    0.72
    itatively
    0.70
     RELE
    0.70
     writ
    0.70
    reading
    0.68
    Activations Density 0.015%

    No Known Activations