© 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. 4963
    Prev
    Next
    INDEX
    Explanations

    mentions of physical hunger

    oai_token-act-pair · gpt-3.5-turbo

    references to hunger and related conditions

    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
    Rub
    -0.70
    thal
    -0.69
     Conduct
    -0.68
     licensed
    -0.68
    VC
    -0.66
     MX
    -0.66
    arthed
    -0.66
     Boll
    -0.65
    tex
    -0.64
     Ruff
    -0.64
    POSITIVE LOGITS
     hunger
    4.16
     Hunger
    2.16
     thirst
    2.14
     starvation
    1.91
     hungry
    1.83
     famine
    1.75
     malnutrition
    1.57
     appetite
    1.53
     starving
    1.46
     craving
    1.41
    Activations Density 0.016%

    No Known Activations