© 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. 0-RES-JB
    11. 5369
    Prev
    Next
    INDEX
    Explanations

    names or terms related to someone or something called "Stub" in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific entities or branded terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Guardians
    -0.77
    osa
    -0.77
     cz
    -0.77
    ghazi
    -0.72
     bil
    -0.71
     Andersen
    -0.70
    amaz
    -0.69
    lette
    -0.68
    itan
    -0.66
     GG
    -0.64
    POSITIVE LOGITS
     Stub
    3.65
     stub
    2.42
     Qualcomm
    1.87
     Snapdragon
    1.21
    Qual
    1.08
     Uri
    1.00
    spoken
    1.00
     supp
    0.95
     Bagg
    0.95
     Tac
    0.94
    Activations Density 0.066%

    No Known Activations