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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 13865
    Prev
    Next
    INDEX
    Explanations

    terms related to dynamic data or processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dynamic qualities or properties in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ador
    -0.91
    mare
    -0.85
    amar
    -0.79
    ACA
    -0.74
    chen
    -0.73
    krit
    -0.73
    acular
    -0.71
    vest
    -0.71
    itude
    -0.70
    hemat
    -0.70
    POSITIVE LOGITS
     Duo
    1.02
     analy
    0.85
     duo
    0.75
     Dynam
    0.71
    motion
    0.71
     electricity
    0.69
     equilibrium
    0.69
    ity
    0.67
     Stability
    0.66
     DNS
    0.66
    Activations Density 0.044%

    No Known Activations