© 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. 10604
    Prev
    Next
    INDEX
    Explanations

    locations or places with the word "Springs" in the name

    oai_token-act-pair · gpt-3.5-turbo

    mentions of geographic locations, particularly cities or towns

    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
    •isco
    #3 activation: 12.23

    No Comments

    Negative Logits
     sacrific
    -0.76
    reader
    -0.70
    intern
    -0.69
    ilater
    -0.69
    oire
    -0.68
    ãĤ¯
    -0.68
    rez
    -0.66
    rahim
    -0.65
    breaks
    -0.64
    reed
    -0.63
    POSITIVE LOGITS
     County
    1.16
     Township
    1.16
     Heights
    1.09
     Municipal
    1.04
     Junction
    0.96
     Gardens
    0.92
     suburb
    0.91
     Supervisor
    0.88
     Airport
    0.88
     Village
    0.88
    Activations Density 0.135%

    No Known Activations