© 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. 5658
    Prev
    Next
    INDEX
    Explanations

    adjectives related to positive qualities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to photography and image capture

    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
    ãĤ¡
    -0.86
    verning
    -0.82
    hetamine
    -0.79
    rums
    -0.78
    ulty
    -0.76
    exit
    -0.75
    termination
    -0.75
     preached
    -0.75
    amphetamine
    -0.73
    termin
    -0.73
    POSITIVE LOGITS
     photograph
    2.07
     photographer
    2.06
     photographs
    2.04
     photograp
    2.00
     photographers
    2.00
     photos
    1.99
     Photography
    1.99
     photography
    1.98
     photo
    1.95
     photographic
    1.89
    Activations Density 0.517%

    No Known Activations