© 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. 2842
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences related to rewards, tips, and incentives

    oai_token-act-pair · gpt-3.5-turbo

    references to rewards or incentives related to actions or information being provided

    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
    legraph
    -0.74
    pport
    -0.70
    soDeliveryDate
    -0.70
    limits
    -0.69
    pect
    -0.69
    types
    -0.65
    æĦ
    -0.65
    eda
    -0.63
    eneg
    -0.63
    ise
    -0.62
    POSITIVE LOGITS
     deeds
    1.11
     referrals
    1.04
     successes
    1.00
     completing
    0.99
     contributions
    0.99
     mistakes
    0.96
     discoveries
    0.92
     failures
    0.92
     conversions
    0.92
     actions
    0.90
    Activations Density 0.238%

    No Known Activations