© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3565
    Prev
    Next
    INDEX
    Explanations

    tech-related terms, such as software names and company names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific technology companies and their products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sylv
    -0.48
     glim
    -0.46
     Beir
    -0.45
    Keefe
    -0.44
     Vaugh
    -0.44
     Azerb
    -0.43
    herer
    -0.39
     anecd
    -0.39
    cules
    -0.39
     UNCLASSIFIED
    -0.38
    POSITIVE LOGITS
     Latest
    0.60
     Anniversary
    0.47
     Released
    0.43
     Secrets
    0.42
     Quote
    0.41
     Its
    0.41
    malink
    0.40
     Release
    0.39
     2018
    0.39
     Highest
    0.39
    Activations Density 0.974%

    No Known Activations