© 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. 3038
    Prev
    Next
    INDEX
    Explanations

    instances where the phrase "you can" is used

    oai_token-act-pair · gpt-3.5-turbo

    expressions of ability or capability

    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
    BuyableInstoreAndOnline
    -0.71
     Returning
    -0.69
     Adin
    -0.69
     Seeking
    -0.68
    é¾įå¥ij士
    -0.68
     Attention
    -0.67
     Passage
    -0.65
    fixes
    -0.64
     RELE
    -0.62
    DeliveryDate
    -0.61
    POSITIVE LOGITS
    't
    1.25
     imagine
    1.20
     bet
    1.09
     expect
    1.07
     argue
    1.06
     see
    0.98
     hear
    0.98
     buy
    0.94
     choose
    0.92
     laugh
    0.92
    Activations Density 0.124%

    No Known Activations