© 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. 10-RES-JB
    6. 901
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences indicating a transition or introductory remark

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating summaries or highlights of information

    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
    ardless
    -0.87
    eligible
    -0.75
    orious
    -0.73
    naires
    -0.73
    uez
    -0.72
    successfully
    -0.71
    existent
    -0.70
    byss
    -0.69
    emale
    -0.69
    enance
    -0.69
    POSITIVE LOGITS
     disclaimer
    1.60
     reminder
    1.54
     note
    1.47
     refres
    1.41
     caveat
    1.41
     clarification
    1.40
     caveats
    1.30
     recap
    1.27
     notes
    1.19
     update
    1.13
    Activations Density 0.195%

    No Known Activations