© 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. 2738
    Prev
    Next
    INDEX
    Explanations

    financial figures and contract details

    oai_token-act-pair · gpt-3.5-turbo

    financial figures and contract details

    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
    emia
    -0.77
     Hast
    -0.73
    microsoft
    -0.69
    uben
    -0.64
    culosis
    -0.63
    icc
    -0.63
    ountain
    -0.62
    sylv
    -0.62
     Straw
    -0.62
     Voices
    -0.61
    POSITIVE LOGITS
     salary
    1.44
     Salary
    1.24
     guaranteed
    1.17
     arbitration
    1.10
     unrestricted
    1.07
     incentives
    1.07
     salaries
    1.06
     2021
    1.06
     bonuses
    1.05
     contract
    1.05
    Activations Density 0.282%

    No Known Activations