© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 6186
    Prev
    Next
    INDEX
    Explanations

    quotations or reported speech

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks and their usage in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Versus
    -0.76
     accomp
    -0.71
     reel
    -0.68
     redes
    -0.65
     XI
    -0.64
     metic
    -0.64
     flourish
    -0.63
     Constitutional
    -0.62
     salute
    -0.62
     banquet
    -0.61
    POSITIVE LOGITS
    there
    1.98
    they
    1.80
    everyone
    1.73
    nob
    1.73
    these
    1.68
    everything
    1.64
    every
    1.63
    someone
    1.59
    many
    1.56
    we
    1.54
    Activations Density 0.214%

    No Known Activations