© 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
    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. 19958
    Prev
    Next
    INDEX
    Explanations

    mentions of the United States (U.S.) and its actions in various international contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the United States

    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
     Noir
    -0.76
     Wicked
    -0.75
     Bach
    -0.69
     CPC
    -0.69
     Cinderella
    -0.66
     juggling
    -0.66
     Preferred
    -0.64
     bars
    -0.63
    ãĥ¯ãĥ³
    -0.62
     Referred
    -0.62
    POSITIVE LOGITS
    prising
    1.22
    nexpected
    1.13
    seless
    0.99
    lyss
    0.98
    gly
    0.96
    NA
    0.93
    prise
    0.92
    zbek
    0.92
    rien
    0.92
    DF
    0.92
    Activations Density 0.054%

    No Known Activations