© 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. 19328
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "dynamic" in the text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dynamic and static data structures or programming concepts

    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
    mare
    -0.82
    mares
    -0.81
    ador
    -0.78
    warts
    -0.74
    amar
    -0.72
    cott
    -0.69
    ĨĴ
    -0.69
    ounces
    -0.68
    akeru
    -0.66
    acular
    -0.66
    POSITIVE LOGITS
     Duo
    0.96
     pricing
    0.82
     analy
    0.80
     equilibrium
    0.77
    ity
    0.75
     balancing
    0.71
     allocation
    0.70
    motion
    0.69
     stretching
    0.69
     duo
    0.69
    Activations Density 0.077%

    No Known Activations