© 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. 6-RES-JB
    11. 12638
    Prev
    Next
    INDEX
    Explanations

    keywords related to software modules and development

    oai_token-act-pair · gpt-3.5-turbo

    references to different modules in a system or software context

    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
    ews
    -0.81
    isconsin
    -0.75
    photo
    -0.75
    WHERE
    -0.69
    vo
    -0.69
    nee
    -0.69
     Guan
    -0.69
     Lauder
    -0.66
     FANTASY
    -0.65
    Ö¼
    -0.65
    POSITIVE LOGITS
     modules
    0.91
     loader
    0.89
    ules
    0.82
     bund
    0.80
    mers
    0.77
    modules
    0.75
    yrinth
    0.73
    matically
    0.69
     vit
    0.69
     module
    0.68
    Activations Density 0.020%

    No Known Activations