© 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. 5103
    Prev
    Next
    INDEX
    Explanations

    mentions of locations, specifically those related to "MO" which likely refers to Missouri

    oai_token-act-pair · gpt-3.5-turbo

    references to the state of Missouri (MO) and associated acronyms

    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
    ãĥ¼ãĥĨãĤ£
    -0.85
    itarian
    -0.79
     Icelandic
    -0.79
    ãĥ³ãĤ¸
    -0.75
     Thrones
    -0.71
    ãĥ´ãĤ¡
    -0.71
    ãĥģ
    -0.71
    wcsstore
    -0.70
    nai
    -0.69
    wealth
    -0.68
    POSITIVE LOGITS
    BIL
    1.01
    ONEY
    1.00
     MO
    0.90
    VE
    0.84
    VO
    0.84
    BI
    0.83
    ORPG
    0.83
    veland
    0.82
    JO
    0.82
    BO
    0.81
    Activations Density 0.003%

    No Known Activations