© 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. 10-RES-JB
    11. 15018
    Prev
    Next
    INDEX
    Explanations

    descriptions related to plants, trees, and their biology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to trees and their ecological aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ghostbusters
    -0.82
    DCS
    -0.81
    POST
    -0.80
     Heist
    -0.79
    76561
    -0.79
    verbal
    -0.78
    VR
    -0.78
    JR
    -0.75
    itime
    -0.74
     Emirates
    -0.73
    POSITIVE LOGITS
     flowering
    1.80
     flowers
    1.70
     plants
    1.65
     trees
    1.65
     vines
    1.65
     seeds
    1.65
     flower
    1.64
     foliage
    1.59
     plant
    1.55
     leaf
    1.53
    Activations Density 0.527%

    No Known Activations