© 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. 546
    Prev
    Next
    INDEX
    Explanations

    the syllable "umi" within words

    oai_token-act-pair · gpt-4-turbo

    Japanese names with characters ending in 'umi.'

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly related to the anime or Japanese media context

    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
    pages
    -0.70
    lain
    -0.70
    drawn
    -0.67
    gling
    -0.65
    space
    -0.62
     slate
    -0.62
     Angry
    -0.61
     incompet
    -0.61
    ²¾
    -0.61
    cies
    -0.61
    POSITIVE LOGITS
    umi
    1.04
    uri
    0.96
    aki
    0.94
     Yen
    0.93
    ya
    0.91
    pta
    0.90
    ás
    0.86
    achi
    0.84
    qa
    0.79
    atsu
    0.77
    Activations Density 0.014%

    No Known Activations