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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 19708
    Prev
    Next
    INDEX
    Explanations

    mentions of homeopathy and related concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to homeopathy and alternative medicine

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Doe
    -0.76
     Grateful
    -0.73
     Fork
    -0.71
     Byrne
    -0.69
     Straw
    -0.67
     Idle
    -0.66
    agos
    -0.66
     Apostle
    -0.65
     Fr
    -0.65
     Squid
    -0.65
    POSITIVE LOGITS
    opathy
    1.26
    opathic
    1.16
     chirop
    0.99
    aceutical
    0.93
     practitioner
    0.91
    upuncture
    0.88
     diagnoses
    0.88
    doctor
    0.88
    opath
    0.87
    apy
    0.84
    Activations Density 0.017%

    No Known Activations