© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 2535
    Prev
    Next
    INDEX
    Explanations

    words related to sports and competition

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to champions or defending titles in competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hops
    -0.90
    zie
    -0.83
    alde
    -0.82
    atorium
    -0.72
    ffe
    -0.71
    ooter
    -0.71
    ombs
    -0.70
    hift
    -0.69
    zin
    -0.69
    eda
    -0.69
    POSITIVE LOGITS
    Nusra
    0.85
    Construct
    0.83
     defending
    0.81
    UFC
    0.70
    ãĥīãĥ©ãĤ´ãĥ³
    0.70
    METHOD
    0.68
    Kings
    0.68
    æĿ
    0.65
    ãĤ¹ãĥĪ
    0.65
    BSD
    0.64
    Activations Density 0.013%

    No Known Activations