© 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. 4310
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases related to returning or resurfacing

    oai_token-act-pair · gpt-3.5-turbo
    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
     Donation
    -0.73
    DAY
    -0.70
    oided
    -0.63
    assium
    -0.62
    claimer
    -0.62
    axter
    -0.61
    Loading
    -0.61
    DERR
    -0.61
    arta
    -0.60
    ounter
    -0.59
    POSITIVE LOGITS
     bloom
    0.93
    NetMessage
    0.90
     widespread
    0.88
     perme
    0.86
     resurgence
    0.85
     ubiqu
    0.82
     pervasive
    0.79
     mainstream
    0.77
     perv
    0.77
     rampant
    0.75
    Activations Density 0.322%

    No Known Activations