© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 408
    Prev
    Next
    INDEX
    Explanations

    titles related to political or social topics

    oai_token-act-pair · gpt-3.5-turbo

    elements related to storytelling or narrative structures

    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
    pora
    -0.77
     Esper
    -0.71
     Carry
    -0.70
     Turing
    -0.69
     analogue
    -0.66
     Preservation
    -0.65
     Poles
    -0.65
     Obst
    -0.61
     Immunity
    -0.61
     Pole
    -0.60
    POSITIVE LOGITS
    embed
    1.01
    gallery
    0.95
    ][/
    0.94
     caption
    0.92
    Thumbnail
    0.90
    iframe
    0.89
    inline
    0.87
     href
    0.86
    Featured
    0.85
     Featured
    0.83
    Activations Density 0.123%

    No Known Activations