© 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. 401
    Prev
    Next
    INDEX
    Explanations

    line breaks or new paragraphs denoted by "Ċ"

    oai_token-act-pair · gpt-4-turbo

    certain types of symbols or characters that are repeated, possibly for emphasis or formatting purposes

    oai_token-act-pair · gpt-3.5-turbo

    instances of political suppression or coercion

    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
     dissu
    -0.74
    ionage
    -0.71
     detract
    -0.66
    awei
    -0.66
    byss
    -0.66
    xual
    -0.65
    igi
    -0.64
    ertodd
    -0.64
    ulkan
    -0.64
    aterasu
    -0.64
    POSITIVE LOGITS
    ccording
    0.98
    ³³³³³³³³³³³³³³³³
    0.94
    Contents
    0.92
    ³³³³
    0.92
    Recent
    0.86
    SPONSORED
    0.85
    Posted
    0.84
    ³³
    0.82
    ³³³
    0.82
    During
    0.81
    Activations Density 0.536%

    No Known Activations