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. 11-RES-JB
    6. 19561
    Prev
    Next
    INDEX
    Explanations

    phrases related to political control and leadership

    oai_token-act-pair · gpt-3.5-turbo

    references to political control and governance related to the Republican Party

    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
     whistlebl
    -0.67
    lied
    -0.63
    emis
    -0.63
     professionalism
    -0.61
     redeem
    -0.61
     mathematician
    -0.58
     Syndrome
    -0.57
     Olymp
    -0.57
    lot
    -0.57
    verty
    -0.56
    POSITIVE LOGITS
     Congress
    1.42
     Legislature
    1.31
     legislatures
    1.29
     legislature
    1.29
     House
    1.26
     congress
    1.26
     senate
    1.20
     Senate
    1.18
    House
    1.12
    Congress
    1.12
    Activations Density 0.182%

    No Known Activations