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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20555
    Prev
    Next
    INDEX
    Explanations

    keywords related to homeopathy and certain medical conditions like encephalopathy

    oai_token-act-pair · gpt-3.5-turbo

    terms related to alternative medicine, specifically homeopathy and its controversy

    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
    Vers
    -0.65
     spotlight
    -0.64
     Ari
    -0.63
     riders
    -0.63
     expectations
    -0.62
     labor
    -0.62
     resolutions
    -0.61
     Fay
    -0.61
     rider
    -0.60
     moments
    -0.59
    POSITIVE LOGITS
    opathy
    4.73
    opathic
    3.73
    opath
    3.70
     pathology
    1.52
    otomy
    1.24
    ocrates
    1.19
     chirop
    1.15
    icter
    1.15
    otherapy
    1.14
    itis
    1.11
    Activations Density 0.018%

    No Known Activations