© 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 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. 4-RES-JB
    11. 16577
    Prev
    Next
    INDEX
    Explanations

    words related to physical doors or door-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to doors and related concepts

    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
    udeb
    -0.70
     Osw
    -0.69
    FUL
    -0.66
    oric
    -0.65
    itars
    -0.64
    anas
    -0.63
    autical
    -0.61
    CENT
    -0.61
    olute
    -0.61
    OTUS
    -0.60
    POSITIVE LOGITS
    door
    1.14
    steps
    1.04
    holes
    0.87
    glers
    0.87
    hole
    0.81
    doors
    0.80
    step
    0.80
    bell
    0.76
    bled
    0.75
    parts
    0.74
    Activations Density 0.017%

    No Known Activations