© 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. 23804
    Prev
    Next
    INDEX
    Explanations

    news headlines containing specific dates or numbers

    oai_token-act-pair · gpt-3.5-turbo

    topics related to health and wellness

    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
     armour
    -0.90
     scrap
    -0.78
     cones
    -0.77
     colours
    -0.75
     pubs
    -0.73
     organised
    -0.72
     isot
    -0.72
     licences
    -0.72
     cone
    -0.72
     dra
    -0.71
    POSITIVE LOGITS
    Enlarge
    1.49
    NPR
    1.10
    Tweet
    0.92
    ccording
    0.92
    WASHINGTON
    0.91
     POLITICO
    0.89
    Posted
    0.88
    ANK
    0.84
    toggle
    0.83
     ********************************
    0.83
    Activations Density 0.132%

    No Known Activations