© 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. 0-RES-JB
    11. 10282
    Prev
    Next
    INDEX
    Explanations

    words related to advancement, promotion, or advocacy

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "promote" and related variations indicating support or encouragement for various causes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Torn
    -0.73
     Option
    -0.70
    umm
    -0.68
     reckoning
    -0.68
    é¾
    -0.67
    lah
    -0.63
    Kit
    -0.63
     Tsukuyomi
    -0.63
     Quarter
    -0.62
    irin
    -0.62
    POSITIVE LOGITS
     promote
    3.17
     promoting
    2.30
     promotes
    2.27
     promoted
    2.01
     promotion
    1.85
     promot
    1.76
     encourage
    1.64
     advertise
    1.55
     promoters
    1.50
     Promotion
    1.44
    Activations Density 0.027%

    No Known Activations