© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 22590
    Prev
    Next
    INDEX
    Explanations

    names, likely with a specific focus on Indian or Middle Eastern names

    oai_token-act-pair · gpt-3.5-turbo

    references to containers or storage concepts, particularly "jar."

    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
    ingham
    -0.70
     Eleven
    -0.67
    ãģį
    -0.65
     SPD
    -0.65
     ATK
    -0.61
     Eater
    -0.60
     exerc
    -0.60
     cheapest
    -0.59
     ATL
    -0.59
     Burgess
    -0.59
    POSITIVE LOGITS
    jar
    1.54
    Jar
    1.11
    zan
    0.89
    lain
    0.86
    bled
    0.85
    zman
    0.84
    rod
    0.83
    jan
    0.83
     Jar
    0.83
    rez
    0.82
    Activations Density 0.006%

    No Known Activations