© 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. 19998
    Prev
    Next
    INDEX
    Explanations

    names of prestigious universities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Princeton University

    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
    orders
    -0.79
    inventory
    -0.72
    ACTION
    -0.72
    AMES
    -0.71
    ifts
    -0.63
    thel
    -0.63
    к
    -0.62
    ternity
    -0.62
    ffect
    -0.61
    ~~~~~~~~~~~~~~~~
    -0.61
    POSITIVE LOGITS
    eton
    0.90
    essors
    0.89
     Princeton
    0.89
    uates
    0.89
    ipal
    0.88
    itri
    0.84
    ilon
    0.84
    essor
    0.82
     physicist
    0.81
     Chapel
    0.81
    Activations Density 0.013%

    No Known Activations