Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 11708
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "closed"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "closed."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Catalog
    -0.78
    aire
    -0.74
    orge
    -0.71
     Lov
    -0.69
    erous
    -0.68
    uana
    -0.68
    arat
    -0.68
    iage
    -0.67
    arta
    -0.66
    ————
    -0.66
    POSITIVE LOGITS
     shutter
    0.85
     doors
    0.79
     closed
    0.79
     throttle
    0.77
     exting
    0.77
     curtains
    0.76
     minded
    0.75
     lid
    0.74
     satell
    0.73
     closures
    0.70
    Activations Density 0.019%

    No Known Activations