© 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
    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. 7434
    Prev
    Next
    INDEX
    Explanations

    information about road closures and related incidents

    oai_token-act-pair · gpt-3.5-turbo

    terms related to closures and restrictions

    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
    esta
    -0.74
    Favorite
    -0.71
     aspir
    -0.68
     empowerment
    -0.68
     ideally
    -0.68
    gem
    -0.68
    Appearance
    -0.67
    milo
    -0.66
     indistinguishable
    -0.63
     excel
    -0.63
    POSITIVE LOGITS
    due
    1.03
     due
    1.03
     indefinitely
    0.91
     owing
    0.90
     outage
    0.89
     curfew
    0.89
     Hurricane
    0.82
     :(
    0.82
     Irma
    0.80
    Due
    0.79
    Activations Density 0.485%

    No Known Activations