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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 6935
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Edward Snowden"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Edward."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Edward

    Explanation Uploaded by User
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roads
    -0.72
    pora
    -0.69
    alore
    -0.69
    hedral
    -0.69
    mobi
    -0.69
    packing
    -0.68
    Äĩ
    -0.68
    sect
    -0.67
    footed
    -0.66
    ionic
    -0.64
    POSITIVE LOGITS
     Snowden
    1.18
     Cullen
    0.91
     Byrne
    0.90
    son
    0.83
     Norton
    0.80
    sson
    0.80
     Herman
    0.78
     Nero
    0.78
     Lans
    0.77
     Gib
    0.76
    Activations Density 0.015%

    No Known Activations