© 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. 4-RES-JB
    11. 16706
    Prev
    Next
    INDEX
    Explanations

    references to a specific sports team - the Browns

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the football team "Browns."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    judicial
    -0.75
    Oracle
    -0.70
    ugal
    -0.70
     erosion
    -0.68
    unct
    -0.68
     Mayer
    -0.68
     endemic
    -0.65
    inel
    -0.65
    sf
    -0.65
    itia
    -0.65
    POSITIVE LOGITS
     Browns
    1.03
    ville
    0.99
     Cavaliers
    0.84
    creen
    0.82
     Hopkins
    0.76
    sburg
    0.74
     Parables
    0.72
    kees
    0.70
     Heights
    0.70
     Crate
    0.70
    Activations Density 0.008%

    No Known Activations