© 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. 9-RES-JB
    11. 2270
    Prev
    Next
    INDEX
    Explanations

    phrases indicating quoted speech or reported statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the reporting or stating of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    twitch
    -0.68
    æĸ
    -0.63
    ä½ľ
    -0.62
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.62
    ãĥĩ
    -0.61
    spread
    -0.60
     Talent
    -0.60
    ivot
    -0.59
    è¯
    -0.57
    sv
    -0.57
    POSITIVE LOGITS
    :"
    0.77
     "...
    0.75
     omin
    0.67
     "âĢ¦
    0.66
     authors
    0.65
     "(
    0.64
    :-
    0.61
     quoting
    0.60
    lishes
    0.59
    :'
    0.59
    Activations Density 0.199%

    No Known Activations