© 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. 20380
    Prev
    Next
    INDEX
    Explanations

    references to various types of plants

    oai_token-act-pair · gpt-3.5-turbo

    references to plants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ROR
    -0.86
    */(
    -0.84
    dash
    -0.80
    pires
    -0.68
    nesota
    -0.66
    alty
    -0.66
    VAL
    -0.65
    VEL
    -0.65
     unden
    -0.64
    olulu
    -0.63
    POSITIVE LOGITS
     plants
    1.35
     Plants
    1.21
     plant
    1.02
     gardens
    0.95
     Plant
    0.90
     farms
    0.84
    ronics
    0.84
     trees
    0.82
    plant
    0.81
     foliage
    0.77
    Activations Density 0.010%

    No Known Activations