© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 2274
    Prev
    Next
    INDEX
    Explanations

    references to safety concerns and emergency situations

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    phrases related to safety concerns or warnings

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ruary
    -0.90
    Truth
    -0.89
    wikipedia
    -0.80
    olkien
    -0.78
    ensable
    -0.78
    Clar
    -0.78
    ivot
    -0.78
    AMA
    -0.77
    minus
    -0.77
    phabet
    -0.76
    POSITIVE LOGITS
     landsl
    1.32
     vandalism
    1.32
     thefts
    1.23
     downed
    1.22
     rodents
    1.20
     graffiti
    1.19
     rodent
    1.18
     looting
    1.17
     wildfires
    1.17
     earthquakes
    1.17
    Activations Density 0.386%

    No Known Activations