© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 24454
    Prev
    Next
    INDEX
    Explanations

    names of fighters in combat sports

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people and their relevance in a context

    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
    ipal
    -0.90
    rollment
    -0.82
    wagen
    -0.80
    ciating
    -0.77
    ADRA
    -0.74
    amental
    -0.73
    vironment
    -0.72
    ãĥ¬
    -0.72
    EngineDebug
    -0.72
    ocene
    -0.71
    POSITIVE LOGITS
    flix
    0.80
    prev
    0.78
    aird
    0.76
    aqu
    0.75
    ack
    0.75
    ubb
    0.71
    agn
    0.71
    una
    0.71
    anqu
    0.70
    ouch
    0.70
    Activations Density 0.017%

    No Known Activations