© 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. 2-RES-JB
    11. 12616
    Prev
    Next
    INDEX
    Explanations

    phrases with honorific titles like 'ji'

    oai_token-act-pair · gpt-3.5-turbo

    references to characters or individuals, particularly those with the suffix "ji."

    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
    lain
    -0.76
    Reviewer
    -0.76
    ilater
    -0.71
    liest
    -0.70
    worldly
    -0.68
    miss
    -0.68
    stories
    -0.67
    mble
    -0.67
    raising
    -0.65
    landish
    -0.64
    POSITIVE LOGITS
    ji
    1.03
    oji
    1.00
    Äĩ
    0.97
    ichi
    0.95
    OSH
    0.94
    itsu
    0.92
    pei
    0.89
    ppe
    0.88
    hei
    0.88
     Yen
    0.87
    Activations Density 0.011%

    No Known Activations