© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3022
    Prev
    Next
    INDEX
    Explanations

    adjectives related to the severity of injuries

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words indicating severe injury or harm

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    relations
    -0.72
    sburgh
    -0.70
    ACY
    -0.69
    yip
    -0.69
    itivity
    -0.68
    uality
    -0.66
    relation
    -0.65
    ords
    -0.64
    ispers
    -0.64
     positives
    -0.63
    POSITIVE LOGITS
     injured
    1.15
     wounded
    1.09
     harmed
    1.04
     damaged
    1.02
     shaken
    1.01
     ill
    1.00
     injuring
    1.00
     endangered
    0.96
     undermined
    0.96
     flawed
    0.94
    Activations Density 0.092%

    No Known Activations