© 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. 16012
    Prev
    Next
    INDEX
    Explanations

    references to different populations in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to different species populations

    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
    quickShipAvailable
    -0.91
    urn
    -0.89
    NESS
    -0.84
    hemy
    -0.80
    rontal
    -0.79
    ension
    -0.79
    sbm
    -0.79
    Child
    -0.78
    INA
    -0.77
    nes
    -0.77
    POSITIVE LOGITS
     populations
    0.85
     inhab
    0.84
     organisms
    0.81
     organism
    0.74
     genetics
    0.74
     flock
    0.73
     genomes
    0.73
    icides
    0.72
     sizes
    0.72
     species
    0.71
    Activations Density 0.012%

    No Known Activations