© 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. 7-RES-JB
    11. 2126
    Prev
    Next
    INDEX
    Explanations

    words related to places or proper names, specifically ones that include the letters "D" and "j"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific places, particularly countries or cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rawdownloadcloneembedreportprint
    -0.73
    姫
    -0.72
     actionGroup
    -0.69
    iflower
    -0.69
     Dragonbound
    -0.69
    sight
    -0.69
    thro
    -0.64
    ulators
    -0.63
    corn
    -0.62
     popcorn
    -0.62
    POSITIVE LOGITS
    ör
    0.95
    inn
    0.93
    ork
    0.92
    arm
    0.91
    anty
    0.90
    ermott
    0.88
    erm
    0.88
    arma
    0.88
    olla
    0.85
    athed
    0.84
    Activations Density 0.032%

    No Known Activations