© 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 EvalsExportsinterp-engineNEWAPI 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. 23087
    Prev
    Next
    INDEX
    Explanations

    locations or addresses

    oai_token-act-pair · gpt-3.5-turbo

    names of sports teams or related statistics

    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
    entimes
    -0.71
    anything
    -0.66
    limits
    -0.65
     enticing
    -0.63
     affordability
    -0.62
     everywhere
    -0.62
    Analy
    -0.61
     tempting
    -0.60
     earnest
    -0.60
     invariably
    -0.60
    POSITIVE LOGITS
     Blvd
    1.17
     Rd
    1.04
     Ave
    1.02
    estamp
    0.71
     RD
    0.70
     âľĵ
    0.68
     Ft
    0.68
    è¦ļéĨĴ
    0.68
     St
    0.67
     acres
    0.67
    Activations Density 0.421%

    No Known Activations