© 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. 0-RES-JB
    11. 1961
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hybrids
    -0.70
     drones
    -0.64
     renewal
    -0.63
     aggregation
    -0.61
     platforms
    -0.60
     subsidies
    -0.59
     connectivity
    -0.59
    .ãĢį
    -0.58
     margins
    -0.58
     2019
    -0.57
    POSITIVE LOGITS
    ickr
    0.69
    dim
    0.67
     Muss
    0.67
     cous
    0.66
    nown
    0.65
    eping
    0.65
     Sic
    0.65
    bent
    0.64
    pure
    0.64
     Herm
    0.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.