© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 13522
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to hunger and starvation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to hunger and starvation

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    afort
    -0.77
    CENT
    -0.73
    osite
    -0.70
    ree
    -0.70
    pheus
    -0.67
    oral
    -0.67
    rious
    -0.66
    Cloud
    -0.65
     Correct
    -0.65
    Sphere
    -0.65
    POSITIVE LOGITS
     starve
    1.23
     starving
    1.05
     starvation
    1.04
     starved
    0.95
     famine
    0.88
     miser
    0.87
     malnutrition
    0.78
    hyde
    0.76
     labou
    0.76
     sacrific
    0.75
    Activations Density 0.024%

    No Known Activations