© 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. 2-RES-JB
    11. 4465
    Prev
    Next
    INDEX
    Explanations

    discount-related terms such as "coupon" and "rebate."

    oai_token-act-pair · gpt-3.5-turbo

    references to coupons, promotions, and rebates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hma
    -0.77
    uther
    -0.73
    Ł
    -0.71
    amed
    -0.71
    hm
    -0.69
    fell
    -0.68
    inct
    -0.67
    TPPStreamerBot
    -0.67
    ¯¯
    -0.66
    igating
    -0.65
    POSITIVE LOGITS
     coupons
    1.38
     coupon
    1.17
     lapse
    0.83
     Coup
    0.82
    ļéĨĴ
    0.81
     redeem
    0.79
    andise
    0.76
    oleon
    0.76
     promo
    0.72
     expiration
    0.72
    Activations Density 0.007%

    No Known Activations