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. 11-RES-JB
    6. 8670
    Prev
    Next
    INDEX
    Explanations

    terms related to processes or factors influencing various phenomena

    oai_token-act-pair · gpt-3.5-turbo

    clauses or phrases that introduce or relate to various processes and factors

    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
    taboola
    -0.71
    ione
    -0.70
    Compar
    -0.68
    ional
    -0.65
    Returns
    -0.65
    ebin
    -0.61
    Ble
    -0.61
    itch
    -0.61
    WER
    -0.60
    oll
    -0.60
    POSITIVE LOGITS
     underpin
    1.35
     govern
    1.31
     characterize
    1.17
     comprise
    1.15
     compose
    1.14
     define
    1.13
     constitute
    1.10
     regulate
    1.08
     populate
    1.05
     governs
    1.04
    Activations Density 0.150%

    No Known Activations