© 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. 9-RES-JB
    11. 17408
    Prev
    Next
    INDEX
    Explanations

    names of individuals, potentially related to news, activities, or events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of people's names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    į
    -0.81
    ãĤ¼
    -0.72
    ÑĮ
    -0.70
    sembly
    -0.70
    pron
    -0.69
    ãĤµ
    -0.68
    ×Ļ×
    -0.67
    %%%%
    -0.67
    rium
    -0.66
    mble
    -0.66
    POSITIVE LOGITS
    's
    0.89
     himself
    0.86
     herself
    0.86
     testified
    0.84
     admits
    0.80
     admitted
    0.78
     remembers
    0.77
     wrote
    0.76
     recalls
    0.76
     participated
    0.75
    Activations Density 0.209%

    No Known Activations