© 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. 9-RES-JB
    11. 7539
    Prev
    Next
    INDEX
    Explanations

    the word "premium"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "premium" and its context in various discussions of value and quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    prototype
    -0.77
    ADRA
    -0.73
    udi
    -0.70
    alf
    -0.68
    wright
    -0.67
    mable
    -0.67
    arming
    -0.66
    swick
    -0.66
    Published
    -0.64
    İĭ
    -0.63
    POSITIVE LOGITS
    cedes
    0.89
     premium
    0.77
    iator
    0.76
    ONSORED
    0.76
     privileges
    0.75
     grade
    0.72
     income
    0.71
     fare
    0.69
     pricing
    0.68
    ensable
    0.68
    Activations Density 0.037%

    No Known Activations