© 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. 10-RES-JB
    11. 10279
    Prev
    Next
    INDEX
    Explanations

    specific parts of a physical location or object

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to agreements and physical objects or locations

    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
    ometimes
    -0.70
    ync
    -0.68
    peed
    -0.60
    cale
    -0.59
    DragonMagazine
    -0.59
    IDES
    -0.57
    Ô
    -0.56
     Scot
    -0.56
    conservancy
    -0.56
    NetMessage
    -0.55
    POSITIVE LOGITS
     itself
    1.40
    's
    0.86
     herself
    0.80
     portion
    0.78
     himself
    0.73
    wright
    0.72
    keeper
    0.71
     yourself
    0.68
    grounds
    0.66
     themselves
    0.65
    Activations Density 0.462%

    No Known Activations