© 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. 2-RES-JB
    11. 17342
    Prev
    Next
    INDEX
    Explanations

    names related to motorsports

    oai_token-act-pair · gpt-3.5-turbo

    names associated with specific individuals involved in a context of performance or conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.90
    utical
    -0.88
    ulhu
    -0.81
    netflix
    -0.79
     WATCHED
    -0.77
    izon
    -0.77
    agascar
    -0.74
     Flavoring
    -0.72
    ories
    -0.70
    hemy
    -0.69
    POSITIVE LOGITS
    ettel
    1.18
    andowski
    0.88
    uder
    0.88
     Alonso
    0.86
    =-=-=-=-=-=-=-=-
    0.82
     lapt
    0.80
    bach
    0.76
    enburg
    0.75
    ctrl
    0.75
    gart
    0.74
    Activations Density 0.020%

    No Known Activations