© 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. 0-RES-JB
    11. 5053
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic activities like pricing and discounts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to inflated prices and discounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     verbs
    -0.79
     verb
    -0.76
    olor
    -0.73
    itect
    -0.72
     Communication
    -0.69
     Sever
    -0.68
     horizont
    -0.67
    ateral
    -0.66
    oming
    -0.63
     interruption
    -0.62
    POSITIVE LOGITS
     discounted
    1.96
     inflated
    1.92
     QC
    1.52
    verified
    1.45
    Featured
    1.36
    confirmed
    1.29
     branded
    1.10
     IPCC
    1.06
     exaggerated
    1.02
     discredited
    1.02
    Activations Density 0.065%

    No Known Activations