© 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. 7210
    Prev
    Next
    INDEX
    Explanations

    sections with unusual characters, potentially indicating metadata or formatting instructions in the document

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and related formatting elements

    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
    ĸļ
    -0.88
     answ
    -0.86
    hement
    -0.79
    xual
    -0.76
     scrap
    -0.73
    ername
    -0.72
     submar
    -0.72
    uca
    -0.71
     purs
    -0.71
     grop
    -0.71
    POSITIVE LOGITS
    References
    0.88
    Posted
    0.88
    Trivia
    0.86
    Premium
    0.85
    ³³³³³³³³³³³³³³³³
    0.85
    ------------------------
    0.83
    ================================================================
    0.82
    Reviewed
    0.82
    Package
    0.81
    Loading
    0.80
    Activations Density 0.737%

    No Known Activations