© 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. 2-RES-JB
    11. 21939
    Prev
    Next
    INDEX
    Explanations

    names related to a person named Connor

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the name Connor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ļ
    -0.81
    ĺħ
    -0.74
    ļé
    -0.73
     circ
    -0.69
    ł
    -0.69
    ª
    -0.66
    ŀ
    -0.66
     quint
    -0.65
    Ĥ¬
    -0.63
    ¢
    -0.63
    POSITIVE LOGITS
    Connor
    1.07
     Connor
    0.98
    raft
    0.86
    hurst
    0.82
    icut
    0.81
     Dixon
    0.78
    patrick
    0.78
     Strait
    0.76
     McKenzie
    0.76
    quist
    0.76
    Activations Density 0.009%

    No Known Activations