© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20217
    Prev
    Next
    INDEX
    Explanations

    news-related information like countries, organizations, events, and political figures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of newsworthy events and reports

    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
     thous
    -0.46
    uyomi
    -0.42
     pse
    -0.41
    ulla
    -0.40
    chuk
    -0.40
    emed
    -0.38
     referen
    -0.38
     warr
    -0.38
     succumbed
    -0.37
     iterations
    -0.36
    POSITIVE LOGITS
     largeDownload
    0.47
     DRAGON
    0.45
    CLOSE
    0.44
     DRAG
    0.43
    rians
    0.41
    ettel
    0.40
    press
    0.40
     PRESS
    0.40
    ktop
    0.39
    pin
    0.39
    Activations Density 3.847%

    No Known Activations