© 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. 1-RES-JB
    11. 21360
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific robot called "Rush."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DER
    -0.70
    SAY
    -0.66
    CM
    -0.65
    Cry
    -0.65
    thy
    -0.63
    RET
    -0.63
     opponent
    -0.62
     atro
    -0.61
     incumb
    -0.61
     Manila
    -0.61
    POSITIVE LOGITS
    vine
    0.74
    bing
    0.71
    stream
    0.70
    76561
    0.67
    bered
    0.67
    guard
    0.64
    photos
    0.62
    acts
    0.62
    bs
    0.62
    azo
    0.61
    Activations Density 0.000%

    No Known Activations