© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 16424
    Prev
    Next
    INDEX
    Explanations

    words related to insects and small animals

    oai_token-act-pair · gpt-3.5-turbo

    references to insects and pests, particularly focusing on moths and ants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Palest
    -0.73
    ctica
    -0.71
    ocaust
    -0.69
    PUT
    -0.69
     Pipeline
    -0.68
    quished
    -0.67
    IST
    -0.66
    UTC
    -0.66
     Gazette
    -0.65
    kus
    -0.64
    POSITIVE LOGITS
     beetles
    1.29
     larvae
    1.26
     beetle
    1.23
    worms
    1.10
    flies
    1.05
     worms
    1.04
     fungus
    1.04
     outbreak
    0.90
     ants
    0.88
     mosquitoes
    0.87
    Activations Density 0.024%

    No Known Activations