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. 8-RES-JB
    6. 16531
    Prev
    Next
    INDEX
    Explanations

    numerical information followed by medical terms

    oai_token-act-pair · gpt-3.5-turbo

    nouns and prefixes related to statistics or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BIL
    -0.65
     ,"
    -0.62
     guiName
    -0.61
    ":[{"
    -0.60
     Trace
    -0.60
     ."
    -0.60
    ãĢIJ
    -0.59
    schild
    -0.57
     Yard
    -0.57
    è¦ļéĨĴ
    -0.57
    POSITIVE LOGITS
    ?)
    1.29
    )
    1.26
    -)
    1.21
    )=
    1.16
    ?),
    1.15
    )/
    1.15
    ),
    1.11
    ?).
    1.09
    +)
    1.09
    )."
    1.09
    Activations Density 0.196%

    No Known Activations