© 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. 10-RES-JB
    11. 18580
    Prev
    Next
    INDEX
    Explanations

    information related to the publication date and details of news articles

    oai_token-act-pair · gpt-3.5-turbo

    publication dates and timestamps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inately
    -0.70
    ably
    -0.65
     Bronx
    -0.61
    âĻ¥
    -0.57
    robe
    -0.56
     grandchildren
    -0.55
     spons
    -0.55
    aterasu
    -0.54
     crest
    -0.54
     retiring
    -0.54
    POSITIVE LOGITS
     IST
    0.75
     DOI
    0.74
    ORPG
    0.73
     doi
    0.70
    çīĪ
    0.69
     mins
    0.66
     dx
    0.65
    Print
    0.65
    olicy
    0.63
    POL
    0.63
    Activations Density 0.050%

    No Known Activations