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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 20222
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the word "Commerce"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Commerce" and related organizations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aze
    -0.68
     MAT
    -0.68
    etr
    -0.67
    768
    -0.61
    WAR
    -0.61
    ractive
    -0.60
    otted
    -0.60
     TIT
    -0.60
     Fury
    -0.59
    oter
    -0.58
    POSITIVE LOGITS
    INESS
    0.90
    andise
    0.83
    cean
    0.77
    ably
    0.72
    merce
    0.72
     commerce
    0.71
    eka
    0.69
    eers
    0.68
     Commerce
    0.67
    assadors
    0.66
    Activations Density 0.043%

    No Known Activations