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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14736
    Prev
    Next
    INDEX
    Explanations

    locations and proper nouns related to the name "Barb"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Barb" or related terms, as well as mentions of "Atari" and "itinerary."

    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
    lights
    -0.74
    lla
    -0.73
    LOS
    -0.69
    nsic
    -0.68
    mberg
    -0.68
    EY
    -0.67
    ITH
    -0.66
    mission
    -0.66
    ggies
    -0.65
    tto
    -0.64
    POSITIVE LOGITS
    ados
    1.04
    urous
    1.03
    raph
    0.97
    agall
    0.92
    anas
    0.88
    ahar
    0.87
    itude
    0.86
    arium
    0.86
    iere
    0.85
    ary
    0.83
    Activations Density 0.016%

    No Known Activations