© 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. 1-RES-JB
    11. 21989
    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
    UGC
    -0.72
    ipal
    -0.71
    itionally
    -0.70
    eny
    -0.70
    udic
    -0.68
    onductor
    -0.67
    ="/
    -0.66
    GER
    -0.65
    agonist
    -0.65
    assadors
    -0.65
    POSITIVE LOGITS
     Quantity
    0.82
     Rates
    0.68
     Speedway
    0.66
     Availability
    0.66
    delay
    0.64
     Lethal
    0.63
    ģ«
    0.62
     Hour
    0.62
     Enix
    0.61
     Rate
    0.61
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.