© 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. 9-RES-JB
    11. 14758
    Prev
    Next
    INDEX
    Explanations

    photography credits in captions

    oai_token-act-pair · gpt-3.5-turbo

    references to images and photo credits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.73
    cible
    -0.71
    nesia
    -0.67
    yip
    -0.66
     debilitating
    -0.66
    floor
    -0.66
    etheless
    -0.62
     unsus
    -0.61
     tranquil
    -0.60
     corros
    -0.60
    POSITIVE LOGITS
     Images
    0.98
     Entertainment
    0.97
     IMAGES
    0.81
     Ltd
    0.79
     Features
    0.78
     Agency
    0.77
    Library
    0.74
     Universe
    0.73
    File
    0.73
     Library
    0.73
    Activations Density 0.030%

    No Known Activations