Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 16830
    Prev
    Next
    INDEX
    Explanations

    specific years indicated in the text

    oai_token-act-pair · gpt-3.5-turbo

    dates or years that signify historical milestones or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wem
    -0.62
     snipp
    -0.57
     Wast
    -0.54
    ashtra
    -0.54
    Jac
    -0.54
    imore
    -0.53
     Danger
    -0.53
     Mens
    -0.52
     Fres
    -0.52
     Sail
    -0.52
    POSITIVE LOGITS
     onwards
    1.05
     onward
    0.94
     inception
    0.83
    when
    0.78
    cffffcc
    0.74
    â̲
    0.70
     when
    0.67
    staking
    0.67
     until
    0.63
    maxwell
    0.62
    Activations Density 0.117%

    No Known Activations