© 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. 5498
    Prev
    Next
    INDEX
    Explanations

    examples illustrating a point or concept

    oai_token-act-pair · gpt-3.5-turbo

    instances of exemplary situations or phenomena

    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
    urses
    -0.84
    ole
    -0.80
     livest
    -0.78
    reditary
    -0.77
    ief
    -0.76
    ensibly
    -0.76
    ternity
    -0.75
    ormal
    -0.75
    aleigh
    -0.73
    rice
    -0.72
    POSITIVE LOGITS
    wcsstore
    0.88
     illustrating
    0.86
    DragonMagazine
    0.85
    baugh
    0.74
     examples
    0.73
     thereof
    0.73
     demonstrating
    0.71
    é¾įå¥ij士
    0.70
     attRot
    0.69
     illustrates
    0.68
    Activations Density 0.031%

    No Known Activations