Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 5663
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of healing

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to healing processes and recovery

    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
    bis
    -0.75
    inet
    -0.74
     Highlights
    -0.72
    MIT
    -0.72
     Bernstein
    -0.71
     Barclays
    -0.68
    sen
    -0.66
    icket
    -0.66
     Dick
    -0.66
     Brent
    -0.65
    POSITIVE LOGITS
     healing
    3.77
     heal
    2.80
     Healing
    2.79
     healed
    2.57
     heals
    2.44
     healer
    2.32
     Heal
    1.82
     Healer
    1.77
     curing
    1.68
     cures
    1.58
    Activations Density 0.014%

    No Known Activations