© 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. 2-RES-JB
    11. 10396
    Prev
    Next
    INDEX
    Explanations

    terms related to superiority or high quality

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "super."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.78
     Seym
    -0.74
    edin
    -0.67
    endor
    -0.61
    EStream
    -0.61
     hed
    -0.61
    gow
    -0.60
    edIn
    -0.60
    ylon
    -0.60
    externalActionCode
    -0.60
    POSITIVE LOGITS
    intendent
    1.27
    visor
    1.22
    ior
    1.14
    visors
    1.03
    vised
    1.02
    visory
    0.91
    marine
    0.88
    natural
    0.87
    conduct
    0.86
    super
    0.85
    Activations Density 0.005%

    No Known Activations