© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 4274
    Prev
    Next
    INDEX
    Explanations

    references to consumption and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to consumption-related topics

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

    No Comments

    Negative Logits
     Spac
    -0.70
     Orion
    -0.69
    interstitial
    -0.63
    beit
    -0.62
     Sharif
    -0.62
     awarding
    -0.61
    inical
    -0.58
     Bom
    -0.57
     Kov
    -0.57
    heed
    -0.56
    POSITIVE LOGITS
     habits
    1.17
     consumption
    0.92
    iture
    0.91
    itures
    0.90
     Consumption
    0.83
     expenditure
    0.81
    ð
    0.79
     expenditures
    0.74
    artifacts
    0.72
    ists
    0.70
    Activations Density 0.014%

    No Known Activations