© 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. 8-RES-JB
    11. 19395
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "reward" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rewards and incentives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abases
    -0.86
     Sloven
    -0.79
    abad
    -0.77
    icago
    -0.71
    uania
    -0.69
    inx
    -0.68
    obiles
    -0.68
     Osw
    -0.67
    ovie
    -0.66
    enium
    -0.66
    POSITIVE LOGITS
     reward
    1.01
     rewards
    0.98
     rewarded
    0.95
     tiers
    0.86
     rewarding
    0.79
     recipients
    0.78
    giving
    0.78
     reap
    0.78
     fulfillment
    0.77
     handsome
    0.74
    Activations Density 0.040%

    No Known Activations