© 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. 19721
    Prev
    Next
    INDEX
    Explanations

    contractions of words, especially those expressing possession like "don't" and "´"

    oai_token-act-pair · gpt-3.5-turbo

    unusual or distinctive punctuation marks

    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
     acknowled
    -0.83
     iceberg
    -0.71
     congr
    -0.70
     aristocracy
    -0.69
     congratulations
    -0.67
    ATURES
    -0.67
     acknow
    -0.66
    lehem
    -0.66
     ashes
    -0.66
    artifacts
    -0.66
    POSITIVE LOGITS
    Tex
    0.78
    -|
    0.74
    elle
    0.72
    _>
    0.70
    Da
    0.70
    olit
    0.69
    Daddy
    0.69
    SEC
    0.68
    Coach
    0.67
    ë
    0.67
    Activations Density 0.000%

    No Known Activations