© 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. 3-RES-JB
    11. 5194
    Prev
    Next
    INDEX
    Explanations

    cave-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to caves

    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
    •Caves

    No Comments

    Negative Logits
    imated
    -0.71
    ICS
    -0.69
     ACTIONS
    -0.68
    pring
    -0.67
    abeth
    -0.67
    NK
    -0.64
    orporated
    -0.63
     ILCS
    -0.63
    icious
    -0.63
     iod
    -0.63
    POSITIVE LOGITS
     cave
    1.13
     caves
    1.01
     Dwell
    0.95
    yrinth
    0.87
     canyon
    0.83
     paintings
    0.80
     dwelling
    0.75
     dwellings
    0.75
     entrances
    0.73
     walls
    0.71
    Activations Density 0.009%

    No Known Activations