© 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. 18759
    Prev
    Next
    INDEX
    Explanations

    URLs referencing specific webpages

    oai_token-act-pair · gpt-3.5-turbo

    web addresses or URLs

    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
     smelling
    -0.91
    Þ
    -0.80
     metic
    -0.80
     behavi
    -0.77
     quir
    -0.76
     Rabbit
    -0.75
    ß
    -0.74
     portraits
    -0.73
     carving
    -0.73
     hemor
    -0.72
    POSITIVE LOGITS
    com
    2.00
    edu
    1.40
    org
    1.40
    COM
    1.32
    net
    1.26
    Com
    1.19
    exe
    1.18
    tv
    1.16
    sites
    1.15
    wordpress
    1.15
    Activations Density 0.035%

    No Known Activations