Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 18851
    Prev
    Next
    INDEX
    Explanations

    phrases related to the slogan "Make America Great Again"

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the word "make" and its variations, particularly in political or transformative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arily
    -0.72
    stration
    -0.64
    anders
    -0.61
     vest
    -0.59
     [+]
    -0.54
    uating
    -0.53
    ?????-
    -0.52
     Investigative
    -0.52
     elic
    -0.52
    uates
    -0.52
    POSITIVE LOGITS
     sure
    1.10
    hift
    1.06
    over
    0.94
     Believe
    0.91
    file
    0.85
    overs
    0.83
    up
    0.83
     Sure
    0.82
     haste
    0.81
    URE
    0.80
    Activations Density 0.037%

    No Known Activations