© 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. 2-RES-JB
    11. 17370
    Prev
    Next
    INDEX
    Explanations

    references to mascots

    oai_token-act-pair · gpt-3.5-turbo

    references to mascots

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    20439
    -0.79
    ×Ļ×
    -0.75
    artz
    -0.71
    ×Ķ
    -0.66
    ardo
    -0.64
     unfocusedRange
    -0.63
    idden
    -0.61
    ighters
    -0.60
    ×ķ
    -0.60
    sight
    -0.60
    POSITIVE LOGITS
     mascot
    1.61
     masc
    1.17
    pole
    0.95
    oji
    0.91
     Haram
    0.84
     costumes
    0.83
    mson
    0.78
     gimmick
    0.75
     costume
    0.75
     gorilla
    0.74
    Activations Density 0.011%

    No Known Activations