© 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. 11-RES-JB
    11. 21464
    Prev
    Next
    INDEX
    Explanations

    instructions or tips related to safety, handling objects, and appliances

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to safety and precautions in household settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Valhalla
    -0.73
    ĺħ
    -0.70
     piracy
    -0.69
     Samoa
    -0.69
    olkien
    -0.68
    "],
    -0.68
     Saga
    -0.67
     Turing
    -0.67
     feats
    -0.66
     propos
    -0.66
    POSITIVE LOGITS
     drainage
    1.13
     moist
    1.08
     indoors
    1.05
     drains
    1.04
     towels
    0.99
     disinfect
    0.99
     moisture
    0.97
     appliances
    0.97
    Avoid
    0.97
     outdoors
    0.95
    Activations Density 0.351%

    No Known Activations