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. 1-RES-JB
    6. 8355
    Prev
    Next
    INDEX
    Explanations

    terms related to dispensing medication or goods

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the dispensing of medication or medical marijuana

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.71
    VEL
    -0.71
    rd
    -0.68
     BaseType
    -0.67
    ENGTH
    -0.67
    GO
    -0.67
    Pros
    -0.66
    RAFT
    -0.65
    GI
    -0.64
    olds
    -0.62
    POSITIVE LOGITS
     dispens
    1.55
    itionally
    0.93
    ership
    0.90
    emonium
    0.88
    ation
    0.87
    otent
    0.86
     concess
    0.83
    emaker
    0.81
    ery
    0.80
    utical
    0.78
    Activations Density 0.010%

    No Known Activations