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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 6378
    Prev
    Next
    INDEX
    Explanations

    words related to alternative medicine, specifically homeopathic treatments and herbal remedies

    oai_token-act-pair · gpt-3.5-turbo

    references to homeopathy and related treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dome
    -0.70
    eat
    -0.66
     Elections
    -0.66
     Transit
    -0.65
     guiActiveUnfocused
    -0.64
     Mutant
    -0.64
     Koen
    -0.64
     Ridley
    -0.63
    patrick
    -0.63
     Conflict
    -0.62
    POSITIVE LOGITS
     remedies
    1.09
     practitioners
    1.05
     practitioner
    1.02
     remedy
    1.01
     medicines
    0.99
     medicine
    0.97
     medicinal
    0.91
     herbal
    0.90
     treatments
    0.87
     supplements
    0.87
    Activations Density 0.062%

    No Known Activations