© 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. 0-RES-JB
    11. 20138
    Prev
    Next
    INDEX
    Explanations

    mentions of political administrations

    oai_token-act-pair · gpt-3.5-turbo

    references to government administrations and their activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cest
    -0.72
     nec
    -0.67
    heed
    -0.66
     location
    -0.65
     Fort
    -0.65
    mount
    -0.64
     royalty
    -0.64
     Pict
    -0.62
    fi
    -0.62
     mystery
    -0.62
    POSITIVE LOGITS
     administrations
    2.23
    essions
    2.07
    uds
    1.64
    ieties
    1.46
     scandals
    1.43
     crises
    1.26
    ourses
    1.13
     failures
    1.13
    alities
    1.09
     secretaries
    1.06
    Activations Density 0.051%

    No Known Activations