© 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. 471
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "src" often used in markup languages or code to denote a source attribute or path

    oai_token-act-pair · gpt-4-turbo

    HTML image sources

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "src" indicating source references or links

    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
    £ı
    -0.94
    awaru
    -0.92
    wagen
    -0.83
    phis
    -0.76
    olulu
    -0.72
    Ń·
    -0.72
    osate
    -0.71
    stood
    -0.71
    etheless
    -0.70
    tarian
    -0.69
    POSITIVE LOGITS
     src
    1.15
    src
    0.97
    natureconservancy
    0.97
     dst
    0.84
    ource
    0.78
    ="/
    0.76
     IMAGES
    0.74
    Contents
    0.74
    layer
    0.74
    cms
    0.73
    Activations Density 0.005%

    No Known Activations