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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 16595
    Prev
    Next
    INDEX
    Explanations

    phrases related to political campaigns

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to elections and candidacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ofi
    -0.86
    âĶĢ
    -0.81
    antine
    -0.81
    illin
    -0.78
    plate
    -0.75
    other
    -0.74
    semble
    -0.71
    atos
    -0.70
     consulted
    -0.70
    ritis
    -0.69
    POSITIVE LOGITS
     reelection
    1.12
     governor
    0.89
     ballot
    0.86
     candidacy
    0.86
     inclusion
    0.84
     redemption
    0.82
     impeachment
    0.80
     captcha
    0.78
    dinand
    0.78
     bids
    0.78
    Activations Density 0.096%

    No Known Activations