© 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. 17146
    Prev
    Next
    INDEX
    Explanations

    mentions of the title or role "President" (Pres) specifically

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "President."

    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
    ItemTracker
    -0.79
     Abyssal
    -0.75
    ļéĨĴ
    -0.74
     shell
    -0.64
     Italians
    -0.64
     Salvation
    -0.64
     Lions
    -0.63
    akespeare
    -0.63
    llah
    -0.63
    loo
    -0.62
    POSITIVE LOGITS
    cription
    1.08
     Pres
    1.04
    erves
    1.02
    Pres
    0.99
    chool
    0.98
    ervation
    0.92
    orial
    0.90
    erving
    0.88
    erve
    0.88
    pres
    0.88
    Activations Density 0.007%

    No Known Activations