© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9531
    Prev
    Next
    INDEX
    Explanations

    mentions of trades or trade-related activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "trade" and related terminology indicating trades or transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jac
    -0.80
    isan
    -0.79
    alach
    -0.77
    idem
    -0.75
    ebin
    -0.74
    iary
    -0.73
    vic
    -0.72
    aum
    -0.71
    english
    -0.71
    andi
    -0.71
    POSITIVE LOGITS
     deadline
    0.98
     Deadline
    0.82
     kicker
    0.82
     waivers
    0.80
     bait
    0.74
     acquisitions
    0.73
    able
    0.73
     arms
    0.68
     paperback
    0.68
     negotiation
    0.68
    Activations Density 0.038%

    No Known Activations