Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 12098
    Prev
    Next
    INDEX
    Explanations

    words related to public announcements or declarations

    oai_token-act-pair · gpt-3.5-turbo

    references to significant announcements or declarations

    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
    asus
    -0.95
    acus
    -0.80
    obos
    -0.78
    opes
    -0.76
    zan
    -0.75
    osph
    -0.75
    iking
    -0.74
    otrop
    -0.74
    uss
    -0.71
    zin
    -0.70
    POSITIVE LOGITS
     announcements
    1.00
     announcement
    0.99
     announcing
    0.92
     announces
    0.92
    eering
    0.88
     Announce
    0.82
     announced
    0.82
     regarding
    0.80
     Countdown
    0.77
     trailer
    0.76
    Activations Density 0.037%

    No Known Activations