© 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. 4-RES-JB
    11. 10633
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to politics and public figures

    oai_token-act-pair · gpt-3.5-turbo

    prominent political figures mentioned in the document

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

    No Comments

    Negative Logits
    olulu
    -0.73
    berra
    -0.65
     Flavoring
    -0.61
    unct
    -0.59
    apter
    -0.58
    reen
    -0.58
    lihood
    -0.56
    20439
    -0.55
    mel
    -0.55
    alys
    -0.54
    POSITIVE LOGITS
     himself
    0.79
     supporters
    0.74
     detractors
    0.72
    's
    0.71
     accuser
    0.69
     TAMADRA
    0.68
    enegger
    0.65
     backers
    0.65
     aides
    0.64
     risked
    0.64
    Activations Density 0.320%

    No Known Activations