© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 7571
    Prev
    Next
    INDEX
    Explanations

    HTML tags

    oai_token-act-pair · gpt-3.5-turbo

    HTML tags and formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÃŃs
    -0.62
     avenues
    -0.58
     intric
    -0.55
     narrator
    -0.55
    vell
    -0.54
     Cinem
    -0.54
    ogical
    -0.54
     restitution
    -0.53
     churn
    -0.52
     looms
    -0.52
    POSITIVE LOGITS
     <
    3.64
    <
    2.55
     <[
    2.44
     <@
    2.34
     </
    2.32
     <+
    2.03
     "<
    1.99
     <!--
    1.91
    </
    1.88
     âī¤
    1.87
    Activations Density 0.014%

    No Known Activations