© 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. 6-RES-JB
    11. 14527
    Prev
    Next
    INDEX
    Explanations

    key concepts or important elements mentioned in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    important concepts or elements within a text

    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
    uthor
    -0.73
     Tsukuyomi
    -0.73
    renheit
    -0.71
     Mile
    -0.70
     Canaver
    -0.69
    AUT
    -0.67
     Chatt
    -0.67
    ibal
    -0.66
     Leaves
    -0.65
    asca
    -0.65
    POSITIVE LOGITS
    stone
    1.26
    stroke
    1.16
    stro
    1.01
    stones
    0.99
    */(
    0.99
    binding
    0.95
    notes
    0.89
    hole
    0.88
    fram
    0.87
    caps
    0.87
    Activations Density 0.026%

    No Known Activations