© 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. 10-RES-JB
    11. 10142
    Prev
    Next
    INDEX
    Explanations

    mentions of government entities

    oai_token-act-pair · gpt-3.5-turbo

    references to government and its roles or responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odox
    -0.81
    actionDate
    -0.76
    ellow
    -0.75
    sembly
    -0.74
    sbm
    -0.74
     guiActiveUn
    -0.72
    uberty
    -0.71
    luaj
    -0.71
     Junction
    -0.71
    anmar
    -0.71
    POSITIVE LOGITS
     collects
    1.17
     wants
    1.12
     considers
    1.09
     deems
    1.08
     regulates
    1.07
     spends
    1.06
     itself
    1.05
     recognizes
    1.04
     intends
    1.04
     owes
    1.04
    Activations Density 0.197%

    No Known Activations