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. 3-RES-JB
    6. 19874
    Prev
    Next
    INDEX
    Explanations

    names of political figures and topics related to politics

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gleaming
    -0.76
    adobe
    -0.76
    isode
    -0.75
    teenth
    -0.73
    orian
    -0.72
    Lex
    -0.72
    ICES
    -0.70
    essor
    -0.70
    ommod
    -0.69
    ãĤ©
    -0.69
    POSITIVE LOGITS
     Abedin
    1.26
     Weiner
    0.99
     Huma
    0.90
     donor
    0.75
     emails
    0.75
     needles
    0.74
     adul
    0.73
     cheated
    0.71
    bed
    0.69
    achment
    0.68
    Activations Density 0.012%

    No Known Activations