© 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. 3047
    Prev
    Next
    INDEX
    Explanations

    mentions of direct or indirect connections, impacts, influences, relationships, or effects between entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to direct and indirect relationships or influences

    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
     Carbuncle
    -0.75
     Klux
    -0.72
     brightest
    -0.71
     brightly
    -0.66
     dearly
    -0.62
     plentiful
    -0.58
     scraps
    -0.57
     cultured
    -0.57
    nox
    -0.55
     Reef
    -0.55
    POSITIVE LOGITS
    meaning
    0.72
    SpaceEngineers
    0.70
     meaning
    0.70
    zzle
    0.69
    arenthood
    0.68
    utor
    0.68
    worthiness
    0.67
    ration
    0.66
    achable
    0.65
    ctive
    0.64
    Activations Density 0.594%

    No Known Activations