© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1-RES-JB
    11. 3402
    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
     Prix
    -0.74
    Construct
    -0.69
    Motion
    -0.65
    Tank
    -0.63
    SL
    -0.63
    tank
    -0.61
     Mechdragon
    -0.61
     Marathon
    -0.60
    riage
    -0.60
    frames
    -0.60
    POSITIVE LOGITS
    psey
    0.91
    aneers
    0.78
    isSpecialOrderable
    0.78
    uploads
    0.76
    fee
    0.76
    osponsors
    0.75
     ingred
    0.72
     guiActiveUn
    0.72
    farious
    0.72
    olicy
    0.72
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.