© 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. 0-RES-JB
    11. 5330
    Prev
    Next
    INDEX
    Explanations

    terms related to maps

    oai_token-act-pair · gpt-3.5-turbo

    references to maps and mapping

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStreamFrame
    -0.82
    ishi
    -0.71
    heter
    -0.70
    harm
    -0.68
     discharged
    -0.67
     Sabha
    -0.66
    airy
    -0.66
     Spir
    -0.66
     Debbie
    -0.65
     Vin
    -0.65
    POSITIVE LOGITS
     maps
    3.77
     Maps
    3.07
    Maps
    2.85
     map
    2.77
    maps
    2.70
     mapping
    2.45
     Map
    2.31
    Map
    2.18
    map
    2.03
     mapped
    1.87
    Activations Density 0.025%

    No Known Activations