© 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. 0-RES-JB
    11. 8223
    Prev
    Next
    INDEX
    Explanations

    quantities or amounts of consumption

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of consumption in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bay
    -0.68
    ision
    -0.66
     Bay
    -0.66
    ror
    -0.63
     nomination
    -0.61
    cy
    -0.61
    bay
    -0.60
     Tactics
    -0.60
     bail
    -0.59
     Miko
    -0.58
    POSITIVE LOGITS
     consumed
    3.70
     consume
    2.39
     eaten
    2.29
     consumes
    2.19
     ingested
    2.06
     consuming
    2.03
     swallowed
    1.74
     consumption
    1.69
     drank
    1.63
     ate
    1.50
    Activations Density 0.010%

    No Known Activations