© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 9904
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences related to names and naming conventions

    oai_token-act-pair · gpt-3.5-turbo

    instances of descriptions and definitions related to names or terms, especially puns and acronyms

    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
    Pros
    -0.81
    rients
    -0.77
     workshops
    -0.74
    verages
    -0.73
    kB
    -0.70
     hrs
    -0.69
     cameras
    -0.68
    ourt
    -0.67
     Costs
    -0.67
    htaking
    -0.66
    POSITIVE LOGITS
     derived
    1.36
     coined
    1.25
     slang
    1.25
     borrowed
    1.24
     shorthand
    1.12
     synonymous
    1.09
     pronounced
    1.06
     shortened
    1.04
     abbre
    1.03
     interchangeable
    1.01
    Activations Density 0.184%

    No Known Activations