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

    Neuronpedia

    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. 17141
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of people

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Rebecca" and its variations

    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
    teenth
    -0.76
    actic
    -0.74
    awaru
    -0.72
    tesque
    -0.67
    igree
    -0.67
    ailand
    -0.66
    arnaev
    -0.66
     dracon
    -0.65
    ramid
    -0.65
    ibaba
    -0.65
    POSITIVE LOGITS
     Rebecca
    0.98
     McKenzie
    0.90
     Lopez
    0.84
     Koen
    0.84
     Upton
    0.83
     Bella
    0.82
     Chal
    0.81
     Mellon
    0.81
    issance
    0.80
     Lazarus
    0.79
    Activations Density 0.012%

    No Known Activations