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. 23669
    Prev
    Next
    INDEX
    Explanations

    specific names of individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    names and terms related to financial institutions and transactions

    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
     Exile
    -0.79
     Harmony
    -0.78
     Anniversary
    -0.75
     Imran
    -0.73
     Illum
    -0.69
     Timeline
    -0.68
     Icon
    -0.68
     Header
    -0.67
     Rowling
    -0.65
     Chronicles
    -0.65
    POSITIVE LOGITS
     Mae
    2.06
     Poe
    1.57
    pri
    1.54
     contr
    1.30
     Nass
    1.19
     sniff
    1.16
     crab
    1.14
    paying
    1.13
     pri
    1.09
    vous
    1.05
    Activations Density 0.044%

    No Known Activations