© 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. 6-RES-JB
    11. 17817
    Prev
    Next
    INDEX
    Explanations

    academic journal titles indicating an area of study related to ecology, political science, psychology, and conflict studies

    oai_token-act-pair · gpt-3.5-turbo

    references to academic publications and related concepts

    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
    adra
    -0.67
     hairc
    -0.66
     resemb
    -0.64
    oooooooo
    -0.63
    andro
    -0.62
    etooth
    -0.62
     curtains
    -0.62
     cures
    -0.61
    dra
    -0.61
     "@
    -0.60
    POSITIVE LOGITS
     Retrieved
    1.16
     PLoS
    0.85
     Edited
    0.78
    ussen
    0.76
    1007
    0.75
    published
    0.74
     Perspect
    0.74
     CRC
    0.74
    Posted
    0.73
     Historical
    0.71
    Activations Density 0.304%

    No Known Activations