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. 9-RES-JB
    6. 22447
    Prev
    Next
    INDEX
    Explanations

    legislative actions and voting outcomes

    oai_token-act-pair · gpt-3.5-turbo

    legislative actions and votes related to government decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     glimps
    -0.69
     Archangel
    -0.68
     exotic
    -0.66
     cov
    -0.65
     seasonal
    -0.65
     hotline
    -0.63
    adian
    -0.62
    mone
    -0.61
     weap
    -0.61
     Typh
    -0.60
    POSITIVE LOGITS
     unanimously
    1.39
     unanimous
    1.32
     votes
    1.31
     vote
    1.24
    animous
    1.14
     overwhelmingly
    1.07
    majority
    1.05
    votes
    1.04
     Votes
    1.03
     majorities
    1.03
    Activations Density 0.357%

    No Known Activations