© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 1900
    Prev
    Next
    INDEX
    Explanations

    speeches or transcripts marked by specific formatting, such as special characters

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and formatting elements within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     citiz
    -0.91
     describ
    -0.88
     eleph
    -0.84
     tiss
    -0.84
    senal
    -0.84
     organis
    -0.84
     neighbourhood
    -0.83
     commissions
    -0.82
     extinct
    -0.81
     prosec
    -0.81
    POSITIVE LOGITS
    SPONSORED
    2.04
    Asked
    1.87
    Trump
    1.83
    ADVERTISEMENT
    1.82
    PHOTOS
    1.80
    CNN
    1.79
    WATCH
    1.77
    Later
    1.75
    Clinton
    1.75
    Democrats
    1.72
    Activations Density 0.350%

    No Known Activations