© 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. 6-RES-JB
    11. 2876
    Prev
    Next
    INDEX
    Explanations

    quantities or numerical information related to a subject

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to numerical quantities and approximations

    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
    Pros
    -0.67
    ModLoader
    -0.66
    inventoryQuantity
    -0.61
    Rap
    -0.61
    ĸļ
    -0.61
    LCS
    -0.61
    Oracle
    -0.59
     reper
    -0.59
    ת
    -0.58
    ACTED
    -0.58
    POSITIVE LOGITS
    pload
    1.00
     dozen
    0.92
    venth
    0.90
    dozen
    0.83
    ousand
    0.82
     thousand
    0.81
    umbo
    0.80
     hundred
    0.80
    teenth
    0.80
    teen
    0.77
    Activations Density 0.047%

    No Known Activations