© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 20432
    Prev
    Next
    INDEX
    Explanations

    words related to plant growth

    oai_token-act-pair · gpt-3.5-turbo

    references to 'buds' and their related concepts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    =#
    -0.73
    INE
    -0.68
    Scotland
    -0.68
    IDES
    -0.68
    ECH
    -0.66
    ESSION
    -0.66
     Mandatory
    -0.65
    Mont
    -0.64
     Presidency
    -0.64
     NEC
    -0.64
    POSITIVE LOGITS
     bud
    1.33
    gie
    1.07
    dh
    1.01
     buds
    0.99
    lio
    0.91
     lapt
    0.81
    mint
    0.80
    gement
    0.80
    keley
    0.78
    nuts
    0.78
    Activations Density 0.003%

    No Known Activations