© 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. 5476
    Prev
    Next
    INDEX
    Explanations

    references to organizations or entities with the word "Kennel" in their names

    oai_token-act-pair · gpt-3.5-turbo

    the end of a document

    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
    DragonMagazine
    -0.78
    etheless
    -0.77
    terday
    -0.77
    worn
    -0.74
    lessly
    -0.71
    ãĥ¬
    -0.69
    ayers
    -0.68
    loo
    -0.66
    ļéĨĴ
    -0.65
    bie
    -0.65
    POSITIVE LOGITS
    alore
    0.83
    eled
    0.78
    efer
    0.74
    apolis
    0.71
    wn
    0.67
    elled
    0.67
    eling
    0.66
    ning
    0.62
    agra
    0.62
    aval
    0.62
    Activations Density 0.080%

    No Known Activations