© 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. 0-RES-JB
    11. 8381
    Prev
    Next
    INDEX
    Explanations

    words related to physical injuries

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "injury" and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    renheit
    -0.74
    mable
    -0.71
     Quartz
    -0.70
     Pars
    -0.69
     SHAR
    -0.68
     Sparrow
    -0.67
    quer
    -0.66
    esters
    -0.65
    Blocks
    -0.65
    trl
    -0.64
    POSITIVE LOGITS
     injury
    3.68
     Injury
    2.94
     injuries
    2.82
     injured
    2.13
    juries
    2.01
     injure
    1.99
    jury
    1.91
     injuring
    1.86
     concussion
    1.61
     illness
    1.60
    Activations Density 0.014%

    No Known Activations