© 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. 10-RES-JB
    11. 13893
    Prev
    Next
    INDEX
    Explanations

    instances where something is being ordered or purchased

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to ordering and purchasing items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ention
    -0.71
    nown
    -0.65
     exert
    -0.63
    Mayor
    -0.62
    laughter
    -0.62
    Politics
    -0.62
    bourg
    -0.62
    SPONSORED
    -0.59
    sworth
    -0.59
    crime
    -0.59
    POSITIVE LOGITS
     yours
    1.09
     TWO
    0.96
     copies
    0.93
     theirs
    0.89
     ONE
    0.89
     them
    0.88
     tickets
    0.87
     Accessories
    0.85
     THREE
    0.83
     mine
    0.82
    Activations Density 0.214%

    No Known Activations