© 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. 3-RES-JB
    11. 11237
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Yeongjongyu" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phonetic sound "ye"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lished
    -0.86
    ahime
    -0.86
    ITY
    -0.77
    ricular
    -0.76
    ities
    -0.75
    itations
    -0.75
    ITAL
    -0.75
    itated
    -0.72
    enhagen
    -0.72
    ctica
    -0.71
    POSITIVE LOGITS
    ye
    1.03
    terday
    0.99
    lde
    0.81
    horn
    0.79
    asure
    0.78
    asing
    0.77
    cker
    0.75
     Mae
    0.75
    xt
    0.74
    ase
    0.72
    Activations Density 0.006%

    No Known Activations