© 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. 8-RES-JB
    11. 22334
    Prev
    Next
    INDEX
    Explanations

    proper names, potentially focusing on names with variations in spelling

    oai_token-act-pair · gpt-3.5-turbo

    the name "Mathias" or variations of it

    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
    ered
    -0.88
    erer
    -0.88
    erers
    -0.83
    ish
    -0.76
    bird
    -0.74
    zie
    -0.73
    shaw
    -0.72
    oys
    -0.71
    ebook
    -0.70
    hammer
    -0.70
    POSITIVE LOGITS
    pora
    1.38
    sembly
    1.35
    aurus
    1.05
    pring
    1.05
    pend
    0.98
    peed
    0.88
    cience
    0.86
    leep
    0.85
    afety
    0.81
    itic
    0.81
    Activations Density 0.110%

    No Known Activations