© 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. 3-RES-JB
    11. 22993
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Patel
    -0.76
     Hansen
    -0.71
     GOODMAN
    -0.70
     Hutch
    -0.69
     Harrington
    -0.66
    Sequ
    -0.65
     Documents
    -0.63
     Ish
    -0.62
     Hav
    -0.62
    ãĢij
    -0.62
    POSITIVE LOGITS
    ablishment
    0.87
    tern
    0.75
    terday
    0.74
    adow
    0.71
    yll
    0.70
    lus
    0.70
    rentices
    0.68
    atl
    0.67
     weakest
    0.67
    gap
    0.66
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.