© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16701
    Prev
    Next
    INDEX
    Explanations

    athlete names with their initials as J.J

    oai_token-act-pair · gpt-3.5-turbo

    references to specific players and their achievements in sports

    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
    cia
    -0.91
    CVE
    -0.81
    Shape
    -0.78
    Correct
    -0.76
    wana
    -0.75
    Disclaimer
    -0.73
    thur
    -0.73
    sth
    -0.71
    SOURCE
    -0.71
    Policy
    -0.70
    POSITIVE LOGITS
     Blaz
    0.90
     Watt
    0.87
     Abrams
    0.86
     Berger
    0.81
     Reynolds
    0.80
     Johnston
    0.77
     Marriott
    0.76
     Stevens
    0.76
     Barrett
    0.76
     Dillon
    0.75
    Activations Density 0.050%

    No Known Activations