© 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. 16772
    Prev
    Next
    INDEX
    Explanations

    mentions of financial institutions and locations

    oai_token-act-pair · gpt-3.5-turbo

    prominent entities such as organizations, locations, and notable individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ãģ¾
    -0.57
    é¾įå¥ij士
    -0.57
    Redd
    -0.57
    Merit
    -0.57
    20439
    -0.55
    ãģĻ
    -0.54
    fx
    -0.54
    ãĥ¥
    -0.54
    Scar
    -0.54
    ãĥ¬
    -0.53
    POSITIVE LOGITS
     consists
    0.80
     lacks
    0.79
     cannot
    0.76
     comprises
    0.75
     differs
    0.74
     fared
    0.73
     underwent
    0.72
     retains
    0.72
     relies
    0.71
     operates
    0.70
    Activations Density 0.834%

    No Known Activations