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. 18077
    Prev
    Next
    INDEX
    Explanations

    the phrase "handful of" followed by other words

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating small quantities or proportions

    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
    YN
    -0.78
     RU
    -0.72
     unfocusedRange
    -0.70
    andra
    -0.70
     GOODMAN
    -0.69
     Skies
    -0.69
    911
    -0.69
    2020
    -0.68
    renched
    -0.67
    burgh
    -0.66
    POSITIVE LOGITS
     (<
    0.86
     trickle
    0.85
     exceptions
    0.74
     scattered
    0.72
     ventured
    0.71
     spots
    0.71
     scratches
    0.70
     inoc
    0.68
     apiece
    0.67
     snippets
    0.67
    Activations Density 0.269%

    No Known Activations