© 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. 17096
    Prev
    Next
    INDEX
    Explanations

    phrases involving punctuation marks and specific words

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly quotation 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
     referen
    -0.85
     thous
    -0.79
     challeng
    -0.70
     corrid
    -0.67
    Ó
    -0.65
    edIn
    -0.64
     Seym
    -0.63
    eday
    -0.63
     convol
    -0.62
     disadvant
    -0.61
    POSITIVE LOGITS
    SELECT
    0.70
    BILITIES
    0.67
     Entered
    0.64
    TEXTURE
    0.62
     SERV
    0.58
     largeDownload
    0.57
    BILITY
    0.57
    Serv
    0.57
    serv
    0.57
    ANS
    0.56
    Activations Density 0.245%

    No Known Activations