© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 12904
    Prev
    Next
    INDEX
    Explanations

    references to government agencies, specifically bureaus

    oai_token-act-pair · gpt-3.5-turbo

    the term "Bureau" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tackle
    -0.67
    rained
    -0.67
    ebook
    -0.66
    Beg
    -0.66
    DonaldTrump
    -0.64
    terday
    -0.63
    isks
    -0.63
     GSL
    -0.63
    vironment
    -0.61
    plays
    -0.60
    POSITIVE LOGITS
    ureau
    1.20
     Bureau
    1.04
    oreal
    0.80
     Merrill
    0.72
     Director
    0.68
     Headquarters
    0.67
    untu
    0.67
     Reporter
    0.66
     bureau
    0.66
     Grizz
    0.64
    Activations Density 0.004%

    No Known Activations