Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 18081
    Prev
    Next
    INDEX
    Explanations

    names of political figures, especially foreign ministers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political figures and their titles

    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
     robbers
    -0.94
    ocene
    -0.77
    bleacher
    -0.67
     thieves
    -0.66
     graveyard
    -0.66
     cemetery
    -0.65
     vag
    -0.65
     tornado
    -0.64
    ãĢı
    -0.64
     Twins
    -0.63
    POSITIVE LOGITS
    etting
    0.73
     ministerial
    0.70
    asury
    0.70
    reet
    0.70
    HUD
    0.69
    WARN
    0.69
     Adviser
    0.69
     UNCLASSIFIED
    0.69
    atform
    0.68
    oub
    0.68
    Activations Density 0.211%

    No Known Activations