© 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. 10-RES-JB
    11. 10616
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or incidents involving potential danger or accidents

    oai_token-act-pair · gpt-3.5-turbo

    narratives or stories relating to personal experiences and broader social commentary

    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
     UNCLASSIFIED
    -1.10
    anasia
    -0.75
    ionage
    -0.70
    vati
    -0.70
     <[
    -0.69
    ļéĨĴ
    -0.67
    ©¶æ
    -0.66
    assad
    -0.66
    apego
    -0.65
    iferation
    -0.64
    POSITIVE LOGITS
     lately
    0.80
     infographic
    0.80
     hilar
    0.78
     frontman
    0.73
     hilarious
    0.72
     catchy
    0.72
     adorable
    0.72
     downright
    0.71
     lucky
    0.70
     savvy
    0.70
    Activations Density 1.553%

    No Known Activations