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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-RES-JB
    6. 21779
    Prev
    Next
    INDEX
    Explanations

    phrases related to the slogan "Make America Great Again" and similar constructions using the word "make"

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "Make" and its variations, often in a political or promotional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vest
    -0.60
    thia
    -0.56
     scrimmage
    -0.56
     Vest
    -0.54
     Singer
    -0.54
     Seat
    -0.54
     bour
    -0.54
    olver
    -0.53
     constitu
    -0.53
     SAR
    -0.53
    POSITIVE LOGITS
     sure
    1.15
    file
    0.94
    hift
    0.92
    Maker
    0.84
    files
    0.83
     Sure
    0.81
    up
    0.79
    peace
    0.78
    chin
    0.76
    make
    0.75
    Activations Density 0.043%

    No Known Activations