© 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. 20896
    Prev
    Next
    INDEX
    Explanations

    numerical data related to quantities or statistics

    oai_token-act-pair · gpt-3.5-turbo

    quantitative terms related to data or statistics

    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
    rison
    -0.64
    cknow
    -0.60
     impat
    -0.60
     Freak
    -0.59
     Ratt
    -0.59
    sonian
    -0.58
     Nid
    -0.57
     Nightmares
    -0.57
     Warwick
    -0.57
     Rocket
    -0.55
    POSITIVE LOGITS
     totaling
    1.32
     apiece
    1.29
     spanning
    1.14
     total
    1.08
     worldwide
    1.08
     globally
    1.05
     nationwide
    1.05
     annually
    1.03
     per
    1.00
     ranging
    0.95
    Activations Density 0.266%

    No Known Activations