© 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 EvalsExportsAPI 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. 2-RES-JB
    11. 15581
    Prev
    Next
    INDEX
    Explanations

    words related to incentivization or rewards

    oai_token-act-pair · gpt-3.5-turbo

    terms related to incentives and rewards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geist
    -0.79
    continental
    -0.78
     Remem
    -0.77
     Liberation
    -0.75
    lust
    -0.73
     ç¥ŀ
    -0.73
     Frag
    -0.70
    can
    -0.67
     Variant
    -0.67
    ivities
    -0.66
    POSITIVE LOGITS
     incentiv
    1.16
     rewarded
    1.10
     rewarding
    0.97
     recipients
    0.83
    urses
    0.79
    AFTA
    0.79
     incent
    0.78
     cultivate
    0.78
     carrot
    0.77
     rewards
    0.77
    Activations Density 0.016%

    No Known Activations