© 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. 11-RES-JB
    11. 17345
    Prev
    Next
    INDEX
    Explanations

    phrases related to homeopathic treatment and practices

    oai_token-act-pair · gpt-3.5-turbo

    terms related to homeopathic treatments and their regulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Passenger
    -0.83
     Strongh
    -0.81
    idable
    -0.74
     hangar
    -0.73
     Grizzlies
    -0.73
     Luffy
    -0.73
     Spawn
    -0.73
    itiveness
    -0.72
     Sounders
    -0.72
    enaries
    -0.72
    POSITIVE LOGITS
     chirop
    1.96
     acupuncture
    1.91
     therapies
    1.79
     herbal
    1.72
     cures
    1.54
     medicine
    1.54
     therapeutic
    1.52
     therapy
    1.45
     treatments
    1.45
     herbs
    1.45
    Activations Density 0.416%

    No Known Activations