© 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. 13554
    Prev
    Next
    INDEX
    Explanations

    references to subsistence-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to subsidies and their impacts

    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
     Letter
    -0.78
    ////////////////////////////////
    -0.71
     Triangle
    -0.70
     Archdemon
    -0.69
    Fax
    -0.68
     Director
    -0.66
     Rome
    -0.66
    Reloaded
    -0.65
     Emperor
    -0.65
    --------------------------------------------------------
    -0.64
    POSITIVE LOGITS
    chool
    1.13
    sembly
    1.11
    isting
    1.10
    itional
    1.04
    ided
    1.02
    umed
    1.02
    oké
    1.02
    itute
    1.01
    umption
    1.01
    iery
    1.01
    Activations Density 0.013%

    No Known Activations