© 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. 1016
    Prev
    Next
    INDEX
    Explanations

    website URLs ending with ".com"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of URLs or 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
     grounding
    -0.77
     scaling
    -0.76
     brackets
    -0.72
     contraction
    -0.71
     marked
    -0.71
     ageing
    -0.71
    TextColor
    -0.70
     leaving
    -0.69
     uphill
    -0.68
     recess
    -0.68
    POSITIVE LOGITS
    com
    1.54
    org
    1.54
    blogspot
    1.50
    wordpress
    1.47
    tumblr
    1.38
    net
    1.34
    yahoo
    1.30
    edu
    1.30
    gmail
    1.29
    info
    1.29
    Activations Density 0.071%

    No Known Activations