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. 19862
    Prev
    Next
    INDEX
    Explanations

    foreign characters, possibly Japanese or Chinese

    oai_token-act-pair · gpt-3.5-turbo

    specific names or titles in a non-English context

    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
    etheless
    -0.89
     compr
    -0.71
     agre
    -0.67
     confir
    -0.64
     commod
    -0.62
     tyr
    -0.62
     unexpected
    -0.60
     concede
    -0.59
     unloaded
    -0.58
     unforeseen
    -0.58
    POSITIVE LOGITS
    ),
    1.72
    )
    1.57
    ?),
    1.57
    )—
    1.54
    ).[
    1.54
    )[
    1.53
     ),
    1.52
    ),"
    1.49
    ?)
    1.47
    /)
    1.45
    Activations Density 0.117%

    No Known Activations