© 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. 1-RES-JB
    11. 9584
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ACTIONS
    -0.78
    venge
    -0.73
    idepress
    -0.66
    lishes
    -0.64
     4090
    -0.64
     consensual
    -0.63
     ãĤ
    -0.61
     derivative
    -0.60
    spec
    -0.59
     ç¥ŀ
    -0.58
    POSITIVE LOGITS
    burgh
    0.75
     Bulgar
    0.71
    ancers
    0.65
    halla
    0.64
     Antiqu
    0.64
    EH
    0.64
     Tribe
    0.64
     Undead
    0.63
     Balk
    0.63
    Shape
    0.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.