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. 14001
    Prev
    Next
    INDEX
    Explanations

    web links and calls to action

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to news updates and newsletters

    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
     Refresh
    -0.73
     refres
    -0.73
     Monstrous
    -0.67
    olitical
    -0.62
     Fisheries
    -0.61
     Ples
    -0.61
     Ars
    -0.60
     Consumption
    -0.59
     Reloaded
    -0.58
     Corpse
    -0.58
    POSITIVE LOGITS
    metics
    0.75
    _-
    0.64
     indo
    0.60
     Sheridan
    0.60
    Tag
    0.59
    Corn
    0.58
    ideon
    0.58
    estamp
    0.58
    DEN
    0.56
    imoto
    0.56
    Activations Density 0.239%

    No Known Activations