© 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. 1-RES-JB
    11. 13860
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Fine Gael," a political party or organization

    oai_token-act-pair · gpt-3.5-turbo

    references to the political party Fine Gael

    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
    PsyNetMessage
    -0.90
     Waterloo
    -0.85
    sworth
    -0.75
    raltar
    -0.75
    leader
    -0.73
    bath
    -0.69
    soDeliveryDate
    -0.69
    adr
    -0.68
    ulator
    -0.67
     Kut
    -0.67
    POSITIVE LOGITS
     Fine
    1.29
    fine
    1.26
    Fine
    1.21
     Gael
    0.98
     fine
    0.98
     tuning
    0.82
    «ĺ
    0.81
    baum
    0.74
    FG
    0.71
    Ĥª
    0.70
    Activations Density 0.008%

    No Known Activations