© 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. 18797
    Prev
    Next
    INDEX
    Explanations

    words related to relieving physical or emotional distress

    oai_token-act-pair · gpt-3.5-turbo

    terms related to relieving or alleviating problems or discomfort

    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
     Cyber
    -0.79
     Values
    -0.74
     copied
    -0.73
    polit
    -0.67
     Egg
    -0.66
     TEAM
    -0.65
     Chess
    -0.65
     Ultron
    -0.65
     Secrets
    -0.64
    isk
    -0.64
    POSITIVE LOGITS
     relieve
    3.00
     relie
    2.78
     alleviate
    2.60
     allev
    2.17
     relief
    2.13
     reliever
    1.79
     Relief
    1.62
     relieved
    1.59
     easing
    1.38
     lessen
    1.35
    Activations Density 0.034%

    No Known Activations