© 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. 15778
    Prev
    Next
    INDEX
    Explanations

    references to a specific person or place, potentially linked to awards, locations, or cultural contexts

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "az" in various forms or contexts

    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
     unexplained
    -0.67
     unsustainable
    -0.66
     plank
    -0.65
     whistle
    -0.65
     credibility
    -0.65
     outp
    -0.61
     ply
    -0.61
     Canterbury
    -0.61
     cannibal
    -0.60
     spir
    -0.60
    POSITIVE LOGITS
    az
    4.32
    AZ
    2.15
    azi
    2.02
    azer
    2.01
    azo
    1.78
    azz
    1.66
    azar
    1.66
    aza
    1.63
    azon
    1.53
    aze
    1.49
    Activations Density 0.010%

    No Known Activations