© 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. 8386
    Prev
    Next
    INDEX
    Explanations

    words related to doors and door-related actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "door."

    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
    ét
    -0.70
    cum
    -0.69
    ocity
    -0.69
    SHARE
    -0.67
    bis
    -0.65
    utan
    -0.64
    TM
    -0.63
    Bet
    -0.60
    utical
    -0.60
    ÃŃn
    -0.59
    POSITIVE LOGITS
     door
    3.76
     doors
    3.04
     Door
    2.72
    door
    2.67
     doorway
    2.23
    doors
    2.02
     Doors
    1.91
     gates
    1.82
     gate
    1.80
     doorstep
    1.76
    Activations Density 0.015%

    No Known Activations