© 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. 11-RES-JB
    11. 6295
    Prev
    Next
    INDEX
    Explanations

    phrases related to making deals or agreements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to deals, agreements, and financial transactions

    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
     Niet
    -0.73
    athered
    -0.63
     hrs
    -0.63
     Creator
    -0.62
     Juda
    -0.59
    utm
    -0.58
    acan
    -0.57
    verages
    -0.57
    ufact
    -0.57
    è¦
    -0.57
    POSITIVE LOGITS
     happen
    1.11
     disappear
    1.03
     available
    1.01
     noises
    1.00
     vanish
    0.93
     payable
    0.92
     unavailable
    0.86
     landfall
    0.83
     easier
    0.83
     possible
    0.83
    Activations Density 0.181%

    No Known Activations