© 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. 0-RES-JB
    11. 8260
    Prev
    Next
    INDEX
    Explanations

    the word "gall" and variations of it

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "gall" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sek
    -0.76
    Ñģ
    -0.72
    е
    -0.72
     Neg
    -0.70
     Buk
    -0.69
     Nancy
    -0.66
     Seek
    -0.65
     Ning
    -0.64
     Ð
    -0.63
     Bu
    -0.63
    POSITIVE LOGITS
     gall
    3.97
    gall
    2.29
    Gall
    2.02
     Gall
    1.65
     Gallagher
    1.36
    spir
    1.07
     Thunderbolt
    0.92
     Karn
    0.87
     ARM
    0.86
     Kil
    0.85
    Activations Density 0.028%

    No Known Activations