© 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. 0-RES-JB
    11. 13979
    Prev
    Next
    INDEX
    Explanations

    proper nouns that are commonly used as names for individuals or organizations

    oai_token-act-pair · gpt-3.5-turbo

    the term "Lead" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     semantic
    -0.80
     nostalgic
    -0.73
     semantics
    -0.72
     cruiser
    -0.70
     zoo
    -0.69
     generational
    -0.65
     tractor
    -0.64
     encyclopedia
    -0.63
     taxis
    -0.63
     eater
    -0.63
    POSITIVE LOGITS
    Lead
    2.77
     Lead
    2.45
    lead
    1.66
     Mald
    1.31
    lime
    1.09
     Grind
    0.96
    lore
    0.96
    onduct
    0.94
     Ment
    0.90
    integ
    0.87
    Activations Density 0.048%

    No Known Activations