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. 5-RES-JB
    6. 14596
    Prev
    Next
    INDEX
    Explanations

    mentions of physical spaces such as closets or drawers

    oai_token-act-pair · gpt-3.5-turbo

    references to storage spaces like closets and drawers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vati
    -0.81
    uana
    -0.69
    iva
    -0.68
    onso
    -0.67
    odic
    -0.66
    idation
    -0.66
    urai
    -0.66
    nesty
    -0.63
    Interstitial
    -0.62
    GH
    -0.62
    POSITIVE LOGITS
     closet
    1.18
    pedia
    0.83
     shelves
    0.79
    leans
    0.76
    ories
    0.76
    glers
    0.74
     cleaners
    0.73
     doors
    0.73
    rities
    0.70
    nuts
    0.69
    Activations Density 0.016%

    No Known Activations