© 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. 12319
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences with a medical treatment context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "treated" in various contexts

    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
    sign
    -0.77
    Pause
    -0.72
    pause
    -0.72
     captcha
    -0.70
    link
    -0.65
     unlocks
    -0.65
    oku
    -0.64
    aron
    -0.64
    omi
    -0.64
    esp
    -0.63
    POSITIVE LOGITS
     treated
    3.60
    treated
    2.62
     treat
    2.05
     treating
    1.97
     untreated
    1.83
     treats
    1.77
     treatment
    1.72
     Treatment
    1.60
     Treat
    1.57
    reated
    1.47
    Activations Density 0.012%

    No Known Activations