© 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. 10-RES-JB
    11. 13789
    Prev
    Next
    INDEX
    Explanations

    that the neuron is looking for phrases indicating someone is about to share information or opinion

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "let me tell you."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hift
    -0.67
    BuyableInstoreAndOnline
    -0.66
    Joined
    -0.60
    untarily
    -0.60
    ©¶æ¥µ
    -0.58
    iband
    -0.57
    calling
    -0.55
    ioned
    -0.54
    =~
    -0.54
    yip
    -0.53
    POSITIVE LOGITS
     guys
    1.14
     somet
    0.90
     why
    0.74
     something
    0.74
     anecd
    0.72
    tub
    0.71
     tonight
    0.70
     Majesty
    0.70
     what
    0.70
    're
    0.70
    Activations Density 0.044%

    No Known Activations