© 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 EvalsExportsinterp-engineNEWAPI 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. 18997
    Prev
    Next
    INDEX
    Explanations

    image captions including the names of photographers or photography agencies

    oai_token-act-pair · gpt-3.5-turbo

    references to image sources and photographers

    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
     awa
    -0.72
    Reviewer
    -0.72
    CONCLUS
    -0.71
     includ
    -0.69
    !!"
    -0.69
    Advertisements
    -0.69
     enthusi
    -0.68
     concluding
    -0.67
    "]=>
    -0.65
    ãĢIJ
    -0.63
    POSITIVE LOGITS
    Courtesy
    1.04
     Courtesy
    0.98
     NPR
    0.92
    ulton
    0.92
    NPR
    0.81
    utterstock
    0.76
    toggle
    0.75
     HBO
    0.72
     Images
    0.71
     Olson
    0.69
    Activations Density 0.013%

    No Known Activations