© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 1090
    Prev
    Next
    INDEX
    Explanations

    words related to history and historical events

    oai_token-act-pair · gpt-3.5-turbo

    phrases and keywords related to history and its impact on the present and future

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entle
    -0.79
     CTR
    -0.76
    IRC
    -0.76
    yip
    -0.75
    reau
    -0.74
     IPM
    -0.73
    SpaceEngineers
    -0.72
    ãĥ³ãĤ¸
    -0.71
    yss
    -0.70
    BILITIES
    -0.69
    POSITIVE LOGITS
     eras
    1.04
     histories
    1.03
     geography
    0.96
     prophe
    0.93
     prol
    0.93
     mythology
    0.92
     flashbacks
    0.90
     heritage
    0.89
     history
    0.88
     historians
    0.88
    Activations Density 0.655%

    No Known Activations