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. 15171
    Prev
    Next
    INDEX
    Explanations

    instances of species and medical terminology

    oai_token-act-pair · gpt-3.5-turbo

    word endings that are characteristic of scientific or academic terminology

    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
    ishers
    -0.94
    ston
    -0.85
    sheet
    -0.82
    ishing
    -0.79
    boards
    -0.78
    isher
    -0.74
    ished
    -0.73
    ered
    -0.73
    ding
    -0.71
    ressing
    -0.70
    POSITIVE LOGITS
    aurus
    1.25
    CRIP
    1.04
    ource
    1.01
    ocial
    0.98
    peed
    0.91
    peria
    0.87
    Magikarp
    0.85
    andra
    0.84
    cular
    0.84
    hift
    0.82
    Activations Density 0.072%

    No Known Activations