© 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. 10-RES-JB
    11. 7970
    Prev
    Next
    INDEX
    Explanations

    announcements and expressions of positivity or excitement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating announcements or expressions of happiness

    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
    ById
    -0.87
    soDeliveryDate
    -0.82
    VERTISEMENT
    -0.73
     aversion
    -0.72
    Downloadha
    -0.70
     Preferences
    -0.65
    ñ
    -0.64
    furt
    -0.62
    puted
    -0.62
     comprehension
    -0.62
    POSITIVE LOGITS
     announce
    1.39
     welcome
    1.14
     introduce
    1.13
     unveil
    1.00
     invite
    0.99
     collaborate
    0.99
     congratulate
    0.98
     hear
    0.97
     endorse
    0.96
     join
    0.95
    Activations Density 0.060%

    No Known Activations