© 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. 9-RES-JB
    11. 10279
    Prev
    Next
    INDEX
    Explanations

    terms related to forestry and environmental conservation

    oai_token-act-pair · gpt-3.5-turbo

    references to forests and forest-related concepts

    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
    soever
    -0.67
    OPLE
    -0.65
     Pric
    -0.62
    pter
    -0.61
    Arcade
    -0.60
    FontSize
    -0.60
    GET
    -0.58
    nor
    -0.58
    HK
    -0.57
    Extra
    -0.56
    POSITIVE LOGITS
    lands
    0.97
     canopy
    0.91
    forest
    0.91
    alling
    0.90
    ãĤ¼ãĤ¦ãĤ¹
    0.87
    mallow
    0.86
    lake
    0.82
     vegetation
    0.80
    omach
    0.79
     forests
    0.79
    Activations Density 0.055%

    No Known Activations