© 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. 4-RES-JB
    11. 15174
    Prev
    Next
    INDEX
    Explanations

    words related to specific objects or items, such as "car", "pie crust", "shoe", "battery", "ball", "firearm", "towel", and "tree"

    oai_token-act-pair · gpt-3.5-turbo

    objects and components related to vehicles and their mechanisms

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

    No Comments

    Negative Logits
    CLASSIFIED
    -0.64
    20439
    -0.63
    CAST
    -0.62
    taboola
    -0.61
    hemy
    -0.61
    VIDIA
    -0.59
     Flavoring
    -0.58
    姫
    -0.57
    terday
    -0.57
    ivism
    -0.57
    POSITIVE LOGITS
     itself
    0.89
     compartment
    0.84
    ultimate
    0.84
    osphere
    0.79
     portion
    0.77
     tray
    0.75
     nearest
    0.73
     enclosure
    0.72
     desired
    0.70
     cavity
    0.70
    Activations Density 0.584%

    No Known Activations