© 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. 9-RES-JB
    11. 15768
    Prev
    Next
    INDEX
    Explanations

    mentions of doors and actions related to doors

    oai_token-act-pair · gpt-3.5-turbo

    references to doors and entry points in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Samoa
    -0.77
    usat
    -0.75
     PNG
    -0.74
    ouble
    -0.72
    GGGG
    -0.71
     GIF
    -0.69
    rities
    -0.69
     SVG
    -0.69
    arget
    -0.67
    conom
    -0.67
    POSITIVE LOGITS
     doors
    1.61
     door
    1.49
     ventilation
    1.33
     Doors
    1.28
     windows
    1.24
     entrances
    1.23
    door
    1.22
     curtains
    1.21
     doorway
    1.21
     Door
    1.19
    Activations Density 0.420%

    No Known Activations