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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    11. 20474
    Prev
    Next
    INDEX
    Explanations

    words related to political or personal interests

    oai_token-act-pair · gpt-3.5-turbo

    references to personal or national interests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¨ãĥ«
    -0.82
    ãĥ£
    -0.69
    ICA
    -0.67
    BuyableInstoreAndOnline
    -0.65
    aston
    -0.65
    ت
    -0.63
    oute
    -0.62
    Je
    -0.62
    é¾į
    -0.62
    aan
    -0.62
    POSITIVE LOGITS
     interests
    0.96
    reprene
    0.90
    hops
    0.80
     parties
    0.74
     collide
    0.73
     agendas
    0.72
    kaya
    0.72
     aligned
    0.70
     territ
    0.70
     Lobby
    0.70
    Activations Density 0.024%

    No Known Activations