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. 301
    Prev
    Next
    INDEX
    Explanations

    quantities or amounts of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of "large amounts" in various contexts

    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
    ħĭ
    -0.85
    resy
    -0.64
     Quote
    -0.63
    gypt
    -0.63
    pr
    -0.63
     Caption
    -0.63
     nearest
    -0.63
    arest
    -0.62
    plant
    -0.62
    ales
    -0.61
    POSITIVE LOGITS
     sorts
    0.86
     resources
    0.71
     Grimm
    0.66
    rontal
    0.63
     calories
    0.63
     antibodies
    0.62
     dollars
    0.60
     interconnected
    0.60
    EVA
    0.60
     concentrated
    0.59
    Activations Density 0.220%

    No Known Activations