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. 8575
    Prev
    Next
    INDEX
    Explanations

    words related to politics and politicians

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political entities or terms

    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
    RED
    -0.71
    uran
    -0.70
     pity
    -0.70
    urous
    -0.69
     Carbuncle
    -0.68
    uring
    -0.67
     Moor
    -0.67
    lamm
    -0.67
    MQ
    -0.66
    URN
    -0.66
    POSITIVE LOGITS
    icians
    1.17
    ifact
    1.10
    ician
    1.03
    icial
    0.96
    ically
    0.94
     Polit
    0.89
    eness
    0.86
     correctness
    0.83
    ique
    0.78
     Pengu
    0.77
    Activations Density 0.009%

    No Known Activations