© 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. 13725
    Prev
    Next
    INDEX
    Explanations

    titles, headings, and subtitles in text related to software tools, technology updates, and company profiles

    oai_token-act-pair · gpt-3.5-turbo

    references to guides, reviews, and testing in contexts related to software or technology

    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
     inertia
    -0.91
     confir
    -0.83
     plaus
    -0.83
     inward
    -0.81
     compr
    -0.81
     overe
    -0.80
     instinct
    -0.79
     incap
    -0.79
     streng
    -0.79
     destro
    -0.78
    POSITIVE LOGITS
     Featuring
    1.20
     Quote
    1.18
     Released
    1.11
     Website
    1.11
     Tags
    1.11
     Overview
    1.10
     Discussion
    1.09
     Posted
    1.09
     Guide
    1.08
     Dates
    1.07
    Activations Density 0.400%

    No Known Activations