© 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. 11-RES-JB
    11. 22146
    Prev
    Next
    INDEX
    Explanations

    phrases related to online shopping actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to transactions or operations involving quantities of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     metic
    -0.88
    ccording
    -0.82
     oun
    -0.77
     proport
    -0.77
     conflic
    -0.77
    senal
    -0.75
     tremend
    -0.73
     exha
    -0.71
     millenn
    -0.71
    ¥ŀ
    -0.70
    POSITIVE LOGITS
    and
    1.01
     and
    0.97
     AND
    0.83
    ands
    0.76
     And
    0.72
    andra
    0.69
    soType
    0.69
    andi
    0.68
    andan
    0.64
     partName
    0.63
    Activations Density 0.058%

    No Known Activations