© 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. 2-RES-JB
    11. 21812
    Prev
    Next
    INDEX
    Explanations

    information related to time, specifically focusing on different quarters of an event or game

    oai_token-act-pair · gpt-3.5-turbo

    terms related to segments of a game or match, particularly referencing quarters and rounds

    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
    anson
    -0.66
    breeding
    -0.65
    beh
    -0.65
     hem
    -0.63
    hern
    -0.63
    lar
    -0.60
     Cosponsors
    -0.59
     dement
    -0.58
     Newsletter
    -0.57
    veh
    -0.56
    POSITIVE LOGITS
    imester
    0.90
    finals
    0.74
    iatus
    0.74
    ĪĴ
    0.70
    ength
    0.69
    estamp
    0.68
    INAL
    0.68
    inals
    0.67
    amide
    0.67
    士
    0.66
    Activations Density 0.087%

    No Known Activations