© 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. 6-RES-JB
    11. 12314
    Prev
    Next
    INDEX
    Explanations

    words related to brand names or entities, likely focusing on finding specific entities starting with "As"

    oai_token-act-pair · gpt-3.5-turbo

    words associated with the character "As" or related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    {"
    -0.66
     Saskatchewan
    -0.66
     Koz
    -0.63
     Zot
    -0.62
     Dragons
    -0.62
     Grayson
    -0.59
     Halls
    -0.58
     Shore
    -0.57
     Ride
    -0.56
     Tigers
    -0.56
    POSITIVE LOGITS
    agus
    0.95
    wered
    0.95
    ream
    0.85
    allah
    0.78
    ylum
    0.76
    nown
    0.75
    ociated
    0.74
    aucas
    0.72
    ãĥ¼ãĤ¯
    0.71
    adesh
    0.71
    Activations Density 0.042%

    No Known Activations