© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5024
    Prev
    Next
    INDEX
    Explanations

    direct quotations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "quoted."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ggles
    -0.77
    ¯¯¯¯
    -0.71
    ét
    -0.71
    venge
    -0.70
    gart
    -0.70
    ¯¯¯¯¯¯¯¯
    -0.70
    ould
    -0.69
     turf
    -0.69
    vic
    -0.68
    estate
    -0.68
    POSITIVE LOGITS
     snippets
    0.99
     quotes
    0.87
     excerpts
    0.84
     phrases
    0.80
     quoting
    0.78
     quoted
    0.77
     sources
    0.76
     unnamed
    0.75
     snippet
    0.70
     extensively
    0.66
    Activations Density 0.015%

    No Known Activations