© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5125
    Prev
    Next
    INDEX
    Explanations

    image sources in HTML code

    oai_token-act-pair · gpt-3.5-turbo

    image source attributes in HTML-like syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    £ı
    -0.93
    theless
    -0.81
     lapse
    -0.74
    osate
    -0.70
    phis
    -0.69
    ocene
    -0.67
    utral
    -0.67
    eering
    -0.66
    ebus
    -0.66
    pherd
    -0.66
    POSITIVE LOGITS
     src
    1.05
    ="/
    0.90
     dst
    0.88
    src
    0.87
    Path
    0.81
    natureconservancy
    0.78
    ~~~~
    0.75
    url
    0.75
    layer
    0.75
    tnc
    0.73
    Activations Density 0.016%

    No Known Activations