© 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. 2-RES-JB
    11. 12787
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names, such as "Sean Spicer" and "HR McMaster"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals associated with political positions or roles

    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
     à¨
    -0.68
    krit
    -0.68
    ĪĴ
    -0.68
    onyms
    -0.67
    yout
    -0.66
    âĸ¬âĸ¬
    -0.66
    itions
    -0.66
    directory
    -0.66
    chest
    -0.65
    itaire
    -0.65
    POSITIVE LOGITS
     Spicer
    1.23
    itzer
    0.82
    andowski
    0.78
     pens
    0.73
     briefings
    0.72
    rites
    0.71
    etz
    0.71
     cones
    0.70
    rer
    0.68
     Osw
    0.68
    Activations Density 0.007%

    No Known Activations