© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 16972
    Prev
    Next
    INDEX
    Explanations

    words related to plant parts, especially leaves

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "leaves" and related terms

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

    No Comments

    Negative Logits
    PDATE
    -0.92
     councill
    -0.75
    AUD
    -0.74
    ALLY
    -0.72
     behavi
    -0.71
    iscopal
    -0.70
     reluct
    -0.69
    ativity
    -0.69
     concess
    -0.68
     referen
    -0.68
    POSITIVE LOGITS
     Leaves
    0.91
    worm
    0.87
    pora
    0.85
     leaves
    0.84
    ings
    0.83
    overs
    0.82
     spores
    0.81
    creen
    0.81
     Chrys
    0.80
    leaf
    0.80
    Activations Density 0.015%

    No Known Activations