© 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. 1-RES-JB
    11. 11573
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Shankar" or "Shankar" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    prominent names and terms associated with political figures or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flo
    -0.72
    Ļ½
    -0.71
    ppy
    -0.69
     QC
    -0.68
     resusc
    -0.67
     textbooks
    -0.66
    Ko
    -0.66
    vell
    -0.66
     cour
    -0.66
     gloss
    -0.63
    POSITIVE LOGITS
    hatt
    0.89
    ivari
    0.88
    ILLE
    0.83
    è¯
    0.83
    avering
    0.79
    ARS
    0.78
    itcher
    0.76
    aver
    0.74
    gue
    0.71
    EngineDebug
    0.71
    Activations Density 0.025%

    No Known Activations