© 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. 3-RES-JB
    11. 20549
    Prev
    Next
    INDEX
    Explanations

    words related to software development, particularly focusing on app development and structuring

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to web application development and architecture

    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
    peria
    -0.91
    emale
    -0.84
    xual
    -0.83
    é¾įå
    -0.81
    ãĥĩãĤ£
    -0.79
    CLASSIFIED
    -0.79
    aucuses
    -0.78
    cffffcc
    -0.76
    åħī
    -0.74
    é¾
    -0.68
    POSITIVE LOGITS
     wrapper
    0.88
     context
    0.85
     library
    0.80
     Container
    0.80
     helper
    0.80
     handler
    0.78
     API
    0.77
     directory
    0.76
     URI
    0.75
     api
    0.74
    Activations Density 0.232%

    No Known Activations