© 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. 10-RES-JB
    11. 716
    Prev
    Next
    INDEX
    Explanations

    words related to physical wounds and injuries

    oai_token-act-pair · gpt-3.5-turbo

    references to wounds and their healing processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.80
    soDeliveryDate
    -0.75
     GEAR
    -0.73
    sat
    -0.71
    rador
    -0.71
    ructose
    -0.71
    hare
    -0.66
    role
    -0.65
    entric
    -0.65
    essions
    -0.65
    POSITIVE LOGITS
     wounds
    1.59
     healed
    1.19
     wound
    1.18
     inflicted
    1.13
     heals
    1.07
     healing
    1.06
     heal
    1.06
     wounded
    1.00
     scars
    0.99
     sore
    0.95
    Activations Density 0.053%

    No Known Activations