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. 6-RES-JB
    6. 4638
    Prev
    Next
    INDEX
    Explanations

    quantities of liquid or solid items, particularly in measurements of ounces

    oai_token-act-pair · gpt-3.5-turbo

    quantities and measurements related to substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     architecture
    -0.83
     militias
    -0.68
    ansson
    -0.65
     performers
    -0.65
     subcontract
    -0.64
     actors
    -0.64
     guarant
    -0.63
     outsourcing
    -0.60
     consultants
    -0.60
     Fighters
    -0.60
    POSITIVE LOGITS
     bottles
    1.13
     bottle
    1.09
     cans
    0.92
    poons
    0.92
     jars
    0.91
     servings
    0.90
     jar
    0.90
    poon
    0.87
     refill
    0.87
     thereof
    0.87
    Activations Density 0.194%

    No Known Activations