© 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. 2921
    Prev
    Next
    INDEX
    Explanations

    titles, headings, or labels in a text document

    oai_token-act-pair · gpt-3.5-turbo

    references to related content or sections

    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
    bably
    -0.85
    idine
    -0.81
    eatures
    -0.76
     tremend
    -0.74
     decoration
    -0.72
     thereafter
    -0.72
    viation
    -0.71
     arrang
    -0.70
     constraint
    -0.70
    urat
    -0.69
    POSITIVE LOGITS
     Why
    1.39
     How
    1.34
     Latest
    1.22
     What
    1.18
     Meet
    1.17
     Inside
    1.14
     Understanding
    1.13
     Could
    1.13
     Recent
    1.13
     Should
    1.12
    Activations Density 0.055%

    No Known Activations