© 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. 1-RES-JB
    11. 21995
    Prev
    Next
    INDEX
    Explanations

    phrases or names containing the substring "ina" with varying contextual meanings

    oai_token-act-pair · gpt-3.5-turbo

    proper names, specifically those ending in "ina."

    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
    keley
    -0.83
    VERTISEMENT
    -0.81
    aeper
    -0.77
    ²¾
    -0.76
    remlin
    -0.75
    irlf
    -0.74
    iple
    -0.73
    yright
    -0.72
    izoph
    -0.71
    ellation
    -0.71
    POSITIVE LOGITS
    BILITY
    1.02
    ina
    1.01
    phrine
    0.90
     Rica
    0.83
    ero
    0.83
    utical
    0.81
    INE
    0.79
    itis
    0.78
    ergic
    0.75
    fter
    0.75
    Activations Density 0.013%

    No Known Activations