© 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. 12799
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to characters or places

    oai_token-act-pair · gpt-3.5-turbo

    specific proper nouns and references to food, particularly broccoli

    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
    arning
    -0.86
    rer
    -0.81
    achment
    -0.77
     Cheong
    -0.70
     Doodle
    -0.69
    oppable
    -0.69
    antis
    -0.69
    igree
    -0.69
    iple
    -0.68
     gol
    -0.67
    POSITIVE LOGITS
     Bran
    0.97
     Stark
    0.78
     burner
    0.72
    illary
    0.72
     Beng
    0.71
    helm
    0.71
    externalActionCode
    0.71
    dylib
    0.67
     cabbage
    0.66
    é»Ĵ
    0.66
    Activations Density 0.023%

    No Known Activations