© 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. 0-RES-JB
    11. 9546
    Prev
    Next
    INDEX
    Explanations

    references to specific locations, possibly related to political events

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or entities related to infrastructure and geography

    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
     Yaz
    -0.63
     disposable
    -0.63
     Chaser
    -0.61
     Caleb
    -0.61
     Pwr
    -0.60
     Data
    -0.58
     Shinji
    -0.58
     arresting
    -0.57
     emanc
    -0.57
     CSI
    -0.56
    POSITIVE LOGITS
    hof
    2.99
     Olympia
    2.10
     Fortress
    1.23
    feet
    1.18
    kamp
    0.98
    ername
    0.84
    aturday
    0.80
     Hercules
    0.79
    enegger
    0.78
    lymp
    0.78
    Activations Density 0.009%

    No Known Activations