© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 407
    Prev
    Next
    INDEX
    Explanations

    the word "seller" or similar variations

    oai_token-act-pair · gpt-3.5-turbo

    the word 'seller'

    oai_token-act-pair · gpt-4-turbo

    references to sellers and selling activities

    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
    viron
    -0.77
    arching
    -0.73
     Mask
    -0.70
    orough
    -0.65
    ournal
    -0.65
    aired
    -0.64
    hens
    -0.64
    uncture
    -0.63
     Brennan
    -0.61
     Archives
    -0.61
    POSITIVE LOGITS
     sellers
    1.08
     seller
    0.99
     beware
    0.92
     mosqu
    0.88
     auctions
    0.85
     discounts
    0.85
     listings
    0.78
     buyers
    0.78
     Seller
    0.76
    igslist
    0.75
    Activations Density 0.007%

    No Known Activations