© 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. 12761
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Terry" with varying suffixes such as "Terner" and "Terlecky"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named "Ter."

    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
    ħĭ
    -0.82
    issance
    -0.77
    ãģ®éŃĶ
    -0.74
    unct
    -0.73
    enthal
    -0.72
    _>
    -0.71
    odcast
    -0.70
    ELS
    -0.69
    BOOK
    -0.68
    ãģį
    -0.68
    POSITIVE LOGITS
    rible
    1.21
    ribly
    1.08
    rigan
    1.05
    ript
    0.99
    race
    0.99
    rance
    0.97
    restrial
    0.96
    rier
    0.96
    abytes
    0.96
    rell
    0.94
    Activations Density 0.007%

    No Known Activations