© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 3278
    Prev
    Next
    INDEX
    Explanations

    references to the term "Anonymous."

    oai_token-act-pair · gpt-3.5-turbo

    references to anonymous sources or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eele
    -0.87
    enegger
    -0.80
    =-=-=-=-=-=-=-=-
    -0.73
    asters
    -0.72
    meaning
    -0.71
    bone
    -0.71
    lux
    -0.70
     Gork
    -0.68
    acts
    -0.67
    oglu
    -0.67
    POSITIVE LOGITS
     Anonymous
    0.89
     obliged
    0.73
     millenn
    0.72
    imedia
    0.71
    ividual
    0.69
    iate
    0.69
    DragonMagazine
    0.65
    TPPStreamerBot
    0.65
    TERN
    0.64
    Anonymous
    0.64
    Activations Density 0.006%

    No Known Activations