© 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. 11-RES-JB
    11. 21017
    Prev
    Next
    INDEX
    Explanations

    mentions of physical injuries and medical conditions, particularly related to bones and bruises

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to injuries and their severity

    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
    soDeliveryDate
    -0.84
    uminati
    -0.84
    iquid
    -0.76
    vironment
    -0.76
    enhagen
    -0.74
    leased
    -0.71
     Waiting
    -0.70
    esters
    -0.70
    quire
    -0.69
    parency
    -0.69
    POSITIVE LOGITS
     concussion
    1.46
     fractures
    1.36
     fractured
    1.28
     amput
    1.28
     bruises
    1.27
     fracture
    1.26
     spinal
    1.26
     injuries
    1.26
     bruising
    1.25
     blows
    1.17
    Activations Density 0.143%

    No Known Activations