© 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. 12833
    Prev
    Next
    INDEX
    Explanations

    phrases related to the introduction or launch of products, services, or initiatives

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the introduction or launch of something

    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
    ucci
    -0.81
     ancest
    -0.67
    eno
    -0.65
     portrayal
    -0.64
    onge
    -0.63
    rouse
    -0.61
    acci
    -0.60
    é¾įåĸļ士
    -0.60
     condu
    -0.59
    Catalog
    -0.59
    POSITIVE LOGITS
     hostilities
    0.74
    glas
    0.67
    xit
    0.61
     these
    0.61
     Moves
    0.58
     Innocent
    0.57
     fresh
    0.57
    leased
    0.57
    ammad
    0.56
    lished
    0.55
    Activations Density 0.157%

    No Known Activations