© 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. 5090
    Prev
    Next
    INDEX
    Explanations

    instances of the word "relief"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of financial or humanitarian assistance

    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
    eton
    -0.72
    rake
    -0.70
    insky
    -0.68
    upload
    -0.67
    agame
    -0.67
    annon
    -0.65
     Kin
    -0.65
     Behavior
    -0.64
     esp
    -0.63
     Paran
    -0.63
    POSITIVE LOGITS
     relief
    4.29
     Relief
    2.95
     relie
    1.84
     relieved
    1.60
     relieve
    1.56
     reliever
    1.46
     allev
    1.34
     remission
    1.29
     aid
    1.27
     rescue
    1.19
    Activations Density 0.005%

    No Known Activations