© 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. 1-RES-JB
    11. 22611
    Prev
    Next
    INDEX
    Explanations

    various numerical codes mixed within the text

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of a specific character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilts
    -0.72
    amiya
    -0.69
     Crest
    -0.67
     handshake
    -0.66
    unta
    -0.64
     Vand
    -0.64
    essel
    -0.63
    othal
    -0.60
    ibrarian
    -0.60
    riott
    -0.60
    POSITIVE LOGITS
    ÂŃ
    0.83
     Appears
    0.78
    deal
    0.78
    nai
    0.74
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.73
    ship
    0.72
    ships
    0.72
    advertisement
    0.71
    advertising
    0.69
    RELATED
    0.69
    Activations Density 0.002%

    No Known Activations