© 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. 6-RES-JB
    11. 19706
    Prev
    Next
    INDEX
    Explanations

    threads and concurrency related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to concurrency and multi-threading in programming

    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
    liam
    -0.84
    bold
    -0.81
    aida
    -0.77
    sonian
    -0.74
    kef
    -0.73
     Betsy
    -0.73
    brand
    -0.72
    eah
    -0.72
    regon
    -0.72
    artisan
    -0.70
    POSITIVE LOGITS
     overhead
    1.12
     debugging
    1.09
     optimizations
    1.08
     optimization
    1.08
     computation
    1.00
     throughput
    1.00
     intensive
    0.99
     sched
    0.97
     runtime
    0.96
     backend
    0.92
    Activations Density 0.203%

    No Known Activations