© 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. 2-RES-JB
    11. 21798
    Prev
    Next
    INDEX
    Explanations

    government and organization URLs

    oai_token-act-pair · gpt-3.5-turbo

    URLs and web addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.78
     Principle
    -0.62
     Mellon
    -0.61
    lyak
    -0.61
     ®
    -0.61
     Scheme
    -0.60
     Gillespie
    -0.60
     Labrador
    -0.59
    SHARE
    -0.59
     «
    -0.58
    POSITIVE LOGITS
    ecd
    0.97
    bd
    0.93
    db
    0.89
    fc
    0.87
    gallery
    0.85
    bb
    0.84
    /?
    0.83
    _
    0.83
    yp
    0.82
    /#
    0.81
    Activations Density 0.370%

    No Known Activations