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. 11-RES-JB
    6. 16266
    Prev
    Next
    INDEX
    Explanations

    terms related to products, purchases, and trade

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technical and agricultural products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interviewer
    -0.82
     circumstance
    -0.72
    yssey
    -0.68
    cknow
    -0.67
    nce
    -0.66
    hunt
    -0.66
     coincidence
    -0.65
    buquerque
    -0.65
    ciation
    -0.65
     onlook
    -0.63
    POSITIVE LOGITS
     goods
    1.50
     products
    1.50
     commodities
    1.30
     merchandise
    1.25
     medicines
    1.19
     items
    1.16
    products
    1.14
     equipment
    1.11
     cigarettes
    1.11
     materials
    1.10
    Activations Density 0.558%

    No Known Activations