© 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. 8-RES-JB
    11. 4281
    Prev
    Next
    INDEX
    Explanations

    the acronym "H.G." occurring alongside other initials or acronyms

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations and titles related to author names, particularly in a literary context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chio
    -0.79
    alogue
    -0.75
    thur
    -0.70
    ãħĭ
    -0.69
    emort
    -0.66
    wcs
    -0.63
    mber
    -0.63
     Guilty
    -0.63
    vic
    -0.59
     Sonia
    -0.59
    POSITIVE LOGITS
    assetsadobe
    1.12
    264
    0.80
    scenes
    0.66
    igans
    0.64
    inton
    0.64
    iday
    0.64
    azard
    0.63
    wire
    0.62
    undreds
    0.62
     Macy
    0.62
    Activations Density 0.050%

    No Known Activations