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. 1-RES-JB
    6. 17958
    Prev
    Next
    INDEX
    Explanations

    references to specific propositions, potentially related to political advocacy

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Prop" followed by a number, indicating references to specific propositions or ballot measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soever
    -0.75
     Carib
    -0.69
    uckle
    -0.69
     Woods
    -0.66
    ä¸ī
    -0.63
     GOODMAN
    -0.63
    ITNESS
    -0.63
     Caribbean
    -0.62
    Interstitial
    -0.61
    ãĤ¼ãĤ¦ãĤ¹
    -0.61
    POSITIVE LOGITS
    aganda
    1.16
    onents
    1.13
    Prop
    1.12
    ylene
    1.01
     Prop
    0.99
    osed
    0.92
    onent
    0.91
    hetically
    0.90
    prop
    0.90
    ulsion
    0.89
    Activations Density 0.009%

    No Known Activations