© 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. 10-RES-JB
    11. 12527
    Prev
    Next
    INDEX
    Explanations

    continuation markers in a text indicating an ongoing or linked discussion

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Article Continued" followed by varying indicators of continuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wives
    -0.62
    haps
    -0.58
     Peb
    -0.58
    esthetic
    -0.58
     Haram
    -0.55
    ofi
    -0.54
     Ans
    -0.54
    ICAN
    -0.54
     tsun
    -0.54
     theoret
    -0.54
    POSITIVE LOGITS
     Below
    1.17
     BELOW
    0.82
     VIDEOS
    0.70
     Continued
    0.70
     Transcript
    0.68
     Loading
    0.67
     Emails
    0.61
     Continue
    0.61
    ...]
    0.59
     fmt
    0.59
    Activations Density 0.006%

    No Known Activations