© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 17219
    Prev
    Next
    INDEX
    Explanations

    mentions of political campaigns and controversial hires

    oai_token-act-pair · gpt-3.5-turbo

    references to political campaigns and social issues related to immigration and representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.75
    Newsletter
    -0.72
     Tsukuyomi
    -0.64
    lihood
    -0.63
     Gors
    -0.62
     thereafter
    -0.61
    RESULTS
    -0.60
    self
    -0.58
    thumbnails
    -0.55
     Kag
    -0.55
    POSITIVE LOGITS
    razil
    0.66
    reetings
    0.64
    nesday
    0.64
     celebrating
    0.61
    ,...
    0.60
    ategory
    0.60
    ursday
    0.60
    aturday
    0.59
    uesday
    0.59
     celebrate
    0.59
    Activations Density 1.411%

    No Known Activations