© 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. 1415
    Prev
    Next
    INDEX
    Explanations

    the phrase "Story Continued Below" followed by specific details or content

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate continuation or ongoing discussion in articles

    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
     federation
    -0.61
    ogy
    -0.59
    士
    -0.57
     recons
    -0.57
     reformed
    -0.56
    bats
    -0.56
     charismatic
    -0.56
     explorers
    -0.56
    models
    -0.55
    usterity
    -0.55
    POSITIVE LOGITS
     Below
    0.91
     Continued
    0.72
    interstitial
    0.70
     Transcript
    0.68
    00200000
    0.66
    etta
    0.64
    aundering
    0.62
     Reading
    0.62
     CNBC
    0.61
     McCain
    0.60
    Activations Density 0.013%

    No Known Activations