© 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. 20094
    Prev
    Next
    INDEX
    Explanations

    references to trees

    oai_token-act-pair · gpt-3.5-turbo

    words related to trees

    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
     doping
    -0.62
     organizer
    -0.59
     catcher
    -0.59
     HC
    -0.58
     easily
    -0.57
     sleeper
    -0.57
     divisive
    -0.57
    administ
    -0.57
     capturing
    -0.57
     pil
    -0.57
    POSITIVE LOGITS
    rees
    4.78
    ree
    2.22
    REE
    1.87
    reed
    1.85
    reements
    1.16
    reek
    1.15
    reen
    1.14
    reet
    1.10
    encies
    1.06
    Tree
    1.03
    Activations Density 0.005%

    No Known Activations