© 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. 8-RES-JB
    11. 7857
    Prev
    Next
    INDEX
    Explanations

    events or occurrences related to press conferences or public announcements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to press conferences and official announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ration
    -0.70
     unlucky
    -0.68
    Cooldown
    -0.68
     dependency
    -0.68
     mars
    -0.67
    livion
    -0.66
     misery
    -0.66
     revenge
    -0.66
     chase
    -0.63
     cubic
    -0.63
    POSITIVE LOGITS
     keynote
    1.38
     attendees
    1.19
     presentations
    1.14
     Attend
    0.97
     Cosponsors
    0.97
     chaired
    0.97
    meet
    0.92
     exhib
    0.92
     podium
    0.91
     delegates
    0.91
    Activations Density 0.593%

    No Known Activations