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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2-RES-JB
    6. 3423
    Prev
    Next
    INDEX
    Explanations

    the name "Hillary Clinton"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Hillary Clinton

    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
    CAP
    -0.79
    ANK
    -0.78
    DIS
    -0.74
    GGGGGGGG
    -0.72
    ITAL
    -0.71
    CAST
    -0.68
     Flavoring
    -0.68
    obe
    -0.67
    gered
    -0.67
    Rex
    -0.66
    POSITIVE LOGITS
     Clinton
    1.03
    Clinton
    1.02
    INTON
    0.86
    clinton
    0.84
     Hillary
    0.82
    istas
    0.82
     Supporters
    0.81
    ite
    0.80
     Rodham
    0.80
     supporters
    0.80
    Activations Density 0.024%

    No Known Activations