© 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. 3-RES-JB
    11. 12735
    Prev
    Next
    INDEX
    Explanations

    references to praise or expressing admiration

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "hail" or its variations, indicating emphasis on acclaim or praise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -1.02
    etsk
    -0.81
    ascript
    -0.79
    atalie
    -0.78
    emy
    -0.76
    ivia
    -0.76
     slightest
    -0.76
     hypot
    -0.75
    olves
    -0.74
    essee
    -0.74
    POSITIVE LOGITS
     hail
    0.99
    STON
    0.84
    owship
    0.78
     Mechdragon
    0.74
    ESH
    0.72
     hailed
    0.72
    BuyableInstoreAndOnline
    0.69
    ãĤ´
    0.68
    CAST
    0.66
     Lightning
    0.65
    Activations Density 0.007%

    No Known Activations