© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 8402
    Prev
    Next
    INDEX
    Explanations

    hyperlinks to websites

    oai_token-act-pair · gpt-3.5-turbo

    URLs and web addresses

    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
     Labrador
    -0.70
     piling
    -0.67
     Fou
    -0.63
     noises
    -0.61
     Skinner
    -0.61
     observed
    -0.61
     misery
    -0.60
     Maher
    -0.60
     tracts
    -0.60
     Redd
    -0.59
    POSITIVE LOGITS
    www
    1.27
    tiny
    1.15
    localhost
    1.07
    goo
    1.07
    natureconservancy
    1.01
     www
    0.97
    opens
    0.90
    http
    0.89
    hess
    0.87
    smart
    0.87
    Activations Density 0.093%

    No Known Activations