© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 22352
    Prev
    Next
    INDEX
    Explanations

    instances of the word "visible."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "visible" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    neg
    -0.87
    berman
    -0.78
    inion
    -0.77
    udeb
    -0.76
    doctor
    -0.76
    ventus
    -0.75
    rieg
    -0.75
    pick
    -0.74
    req
    -0.74
    axter
    -0.73
    POSITIVE LOGITS
     visible
    1.16
     detectable
    0.79
     signs
    0.78
     Signs
    0.77
     VIDEOS
    0.76
     presence
    0.75
     manifestation
    0.72
     âĶľâĶĢâĶĢ
    0.70
     manifestations
    0.70
    visible
    0.69
    Activations Density 0.010%

    No Known Activations