© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 2728
    Prev
    Next
    INDEX
    Explanations

    references to political figures holding the title of "Speaker"

    oai_token-act-pair · gpt-3.5-turbo

    references to political speakers or leaders

    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
     hectares
    -0.68
     haz
    -0.65
    oots
    -0.62
    beans
    -0.61
    illy
    -0.61
    stones
    -0.60
    illas
    -0.60
    ios
    -0.60
    arching
    -0.60
     park
    -0.59
    POSITIVE LOGITS
     Speaker
    4.01
     speaker
    2.54
     speakers
    1.62
     Chair
    1.45
    Spe
    1.40
     Boehner
    1.37
     Treasurer
    1.32
     Chancellor
    1.32
     Majority
    1.30
     Chairman
    1.27
    Activations Density 0.013%

    No Known Activations