© 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. 8-RES-JB
    11. 10720
    Prev
    Next
    INDEX
    Explanations

    credit information with photo credits

    oai_token-act-pair · gpt-3.5-turbo

    images associated with news stories or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ixel
    -0.71
    acity
    -0.71
    stru
    -0.68
    oler
    -0.66
    iveness
    -0.65
    bats
    -0.65
    iqu
    -0.65
    odox
    -0.64
    gae
    -0.64
     continents
    -0.64
    POSITIVE LOGITS
     Courtesy
    1.08
     COURT
    1.03
     Provided
    1.00
     ©
    0.96
     Getty
    0.85
     Associated
    0.83
     REUTERS
    0.82
     Shutterstock
    0.80
     Wikimedia
    0.77
     .)
    0.76
    Activations Density 0.019%

    No Known Activations