© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RES-JB
    11. 16782
    Prev
    Next
    INDEX
    Explanations

    words related to healing

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to healing and recovery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.73
    legal
    -0.66
     Sop
    -0.61
    VP
    -0.61
    urity
    -0.60
    ARGET
    -0.58
    coni
    -0.58
     Skinner
    -0.57
     tagging
    -0.56
    atography
    -0.56
    POSITIVE LOGITS
     wounds
    1.02
    ilitating
    0.97
     heal
    0.94
     healing
    0.89
     heals
    0.83
     healed
    0.82
    erest
    0.81
    strap
    0.74
     ashore
    0.73
     Healing
    0.72
    Activations Density 0.030%

    No Known Activations