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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16421
    Prev
    Next
    INDEX
    Explanations

    references to plants

    oai_token-act-pair · gpt-3.5-turbo
    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
    Uber
    -0.82
    ivities
    -0.79
     Tickets
    -0.72
     Seconds
    -0.71
     Codes
    -0.68
     Equality
    -0.68
    JSON
    -0.67
    govtrack
    -0.66
     Uber
    -0.65
    codes
    -0.64
    POSITIVE LOGITS
     plant
    3.71
     plants
    2.80
     Plant
    2.59
     Plants
    2.28
    plant
    2.20
     planting
    1.54
     planted
    1.40
     vegetation
    1.35
     vine
    1.35
     vegetable
    1.34
    Activations Density 0.011%

    No Known Activations