© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 17725
    Prev
    Next
    INDEX
    Explanations

    occurrences of doors and actions related to doors like opening, closing, and locking

    oai_token-act-pair · gpt-3.5-turbo

    references to doors and their states (open or closed)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.76
    Reloaded
    -0.71
    arus
    -0.69
    ual
    -0.67
    OTAL
    -0.66
    azeera
    -0.65
     EDITION
    -0.62
    utan
    -0.62
     AMERICA
    -0.61
    amily
    -0.59
    POSITIVE LOGITS
    bell
    1.45
    steps
    1.37
    frame
    1.25
    ways
    1.17
    doors
    1.17
    keeper
    1.12
    stop
    1.12
    keepers
    1.11
    frames
    1.09
     knob
    1.08
    Activations Density 0.047%

    No Known Activations