© 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. 7-RES-JB
    11. 21140
    Prev
    Next
    INDEX
    Explanations

    words related to specific video games or game-related terms, particularly "State of the Union" and "World of Warcraft"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "State of" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agher
    -0.68
    halla
    -0.67
    efully
    -0.62
    és
    -0.61
    iest
    -0.61
    achu
    -0.60
    acca
    -0.60
    erest
    -0.59
    ambers
    -0.58
    illion
    -0.57
    POSITIVE LOGITS
     Decay
    0.80
     Plenty
    0.77
     Champions
    0.71
     Duty
    0.70
     Affairs
    0.66
    Sky
    0.65
    wat
    0.61
     Skydragon
    0.61
     Nations
    0.61
    Life
    0.61
    Activations Density 0.122%

    No Known Activations