© 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. 4-RES-JB
    11. 10476
    Prev
    Next
    INDEX
    Explanations

    information related to herbs and pesticides

    oai_token-act-pair · gpt-3.5-turbo

    references to herbs in various contexts

    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
    choes
    -0.73
    hani
    -0.71
     retrospective
    -0.69
     Barcl
    -0.65
     Masquerade
    -0.65
    gaard
    -0.65
     Telegram
    -0.64
    ochet
    -0.64
    --------
    -0.64
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.63
    POSITIVE LOGITS
    aceous
    1.30
    icide
    1.28
    icides
    1.24
    ohydrate
    1.00
    icals
    0.98
     gardens
    0.94
    istry
    0.92
    icidal
    0.90
     herb
    0.87
    ica
    0.86
    Activations Density 0.009%

    No Known Activations