© 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. 0-RES-JB
    11. 5034
    Prev
    Next
    INDEX
    Explanations

    phrases or proper nouns related to the word "Tree"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific trees and faces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     conco
    -0.79
     pir
    -0.78
     vel
    -0.77
     mol
    -0.77
     franc
    -0.77
     orche
    -0.74
     mar
    -0.74
     stew
    -0.74
     pont
    -0.73
     buckle
    -0.73
    POSITIVE LOGITS
     Tree
    2.37
     Face
    1.81
    Face
    1.74
     Leaf
    1.60
     Fac
    1.53
     Seed
    1.53
     Trees
    1.51
     Floor
    1.50
     Faces
    1.50
    Tree
    1.47
    Activations Density 0.042%

    No Known Activations