© 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. 8-RES-JB
    11. 23708
    Prev
    Next
    INDEX
    Explanations

    terms related to serious issues or topics such as medical conditions, war, abuse, and terrorism

    oai_token-act-pair · gpt-3.5-turbo

    references to significant historical events, particularly those related to trauma and certain health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.90
    в
    -0.75
     Tanz
    -0.73
    VERTISEMENT
    -0.72
    ugi
    -0.71
    andum
    -0.70
    hran
    -0.69
    agall
    -0.69
    æ©
    -0.67
    lee
    -0.67
    POSITIVE LOGITS
     themed
    1.13
     enthusiast
    1.07
     prevention
    0.99
     expert
    0.98
    themed
    0.98
     advocacy
    0.88
     awareness
    0.85
     thriller
    0.85
    focused
    0.83
     enthusiasts
    0.83
    Activations Density 0.751%

    No Known Activations