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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3813
    Prev
    Next
    INDEX
    Explanations

    substances or drugs related to chemical compounds

    oai_token-act-pair · gpt-3.5-turbo

    references to various substances, particularly in a context related to drugs and hazards

    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
    éĹ
    -0.71
     hangar
    -0.70
    hower
    -0.67
    arch
    -0.67
     tooltip
    -0.66
    ji
    -0.66
    Center
    -0.65
     guiActiveUnfocused
    -0.64
    hip
    -0.64
    hon
    -0.63
    POSITIVE LOGITS
     substances
    2.67
     drugs
    2.67
     medications
    2.28
     narcotics
    2.17
     Drugs
    2.10
     medicines
    1.85
     hormones
    1.85
     opioids
    1.84
     antidepressants
    1.77
     chemicals
    1.76
    Activations Density 0.034%

    No Known Activations