© 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. 8972
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting markers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    portions of text that are formatted differently than the main body of the text

    oai_token-act-pair · gpt-3.5-turbo
    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
    idth
    -0.50
    illet
    -0.49
    ucer
    -0.49
    poke
    -0.47
    angel
    -0.46
     Goth
    -0.44
     Celebration
    -0.43
    clad
    -0.43
     Crusade
    -0.41
     Birthday
    -0.41
    POSITIVE LOGITS
    SPONSORED
    0.67
     diplom
    0.61
    CVE
    0.56
    Furthermore
    0.54
    Additionally
    0.52
     moreover
    0.51
    Moreover
    0.49
     fung
    0.49
     furthermore
    0.49
     additionally
    0.49
    Activations Density 2.434%

    No Known Activations