© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 15238
    Prev
    Next
    INDEX
    Explanations

    references to rewards or benefits

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to various types of rewards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abases
    -0.82
    abad
    -0.77
     Sloven
    -0.73
    obiles
    -0.70
     Osw
    -0.70
    ahime
    -0.69
    opic
    -0.68
    jen
    -0.68
    colo
    -0.67
    enium
    -0.67
    POSITIVE LOGITS
     reward
    1.05
     rewards
    1.01
     rewarded
    0.95
     rewarding
    0.81
    Reward
    0.77
     reap
    0.77
     recipients
    0.76
     incentive
    0.75
     tiers
    0.74
     Reward
    0.73
    Activations Density 0.024%

    No Known Activations