© 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. 1-RES-JB
    11. 10248
    Prev
    Next
    INDEX
    Explanations

    internet-related terms or references, especially mentioning specific websites like eBay

    oai_token-act-pair · gpt-3.5-turbo

    references to the brand "EB" or "eb" and related products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rawdownloadcloneembedreportprint
    -0.82
    IZE
    -0.72
    tenance
    -0.71
     Franken
    -0.68
     Monsanto
    -0.66
     Gravity
    -0.65
    å£
    -0.65
    Leary
    -0.64
     Greenwald
    -0.63
    Magikarp
    -0.63
    POSITIVE LOGITS
    ruary
    1.07
     Eb
    1.05
     eb
    1.00
    ecause
    1.00
    iqueness
    0.92
    uda
    0.91
    odies
    0.90
    uchi
    0.87
    raham
    0.87
    bs
    0.85
    Activations Density 0.008%

    No Known Activations