© 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. 9-RES-JB
    11. 22733
    Prev
    Next
    INDEX
    Explanations

    words related to herbivores and herbicides

    oai_token-act-pair · gpt-3.5-turbo

    references to herbs and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kou
    -0.66
     Charter
    -0.65
     allegiance
    -0.64
     Doodle
    -0.62
     Zoom
    -0.61
     Stern
    -0.60
     Mongo
    -0.60
     Sandy
    -0.58
     Dunk
    -0.58
     Nile
    -0.58
    POSITIVE LOGITS
    aceous
    1.48
    icide
    1.28
    icides
    1.22
    iv
    1.07
    osate
    1.06
    itate
    1.03
    ophon
    1.00
    icum
    1.00
    ivated
    0.99
    itant
    0.96
    Activations Density 0.095%

    No Known Activations