© 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. 7-RES-JB
    11. 12671
    Prev
    Next
    INDEX
    Explanations

    names of a specific person: Edward Snowden

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Edward" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alore
    -0.75
    pora
    -0.75
    hedral
    -0.69
    mobi
    -0.69
    Äĩ
    -0.67
    cone
    -0.66
    tsky
    -0.66
    asks
    -0.66
    nda
    -0.65
    packing
    -0.65
    POSITIVE LOGITS
     Snowden
    1.07
    son
    0.80
     Cullen
    0.79
    sson
    0.79
     Edward
    0.77
     Nero
    0.77
     Norton
    0.77
     Byrne
    0.75
     Everett
    0.74
     Cornwall
    0.73
    Activations Density 0.015%

    No Known Activations