© 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. 2459
    Prev
    Next
    INDEX
    Explanations

    websites or platforms where users can interact or exchange information

    oai_token-act-pair · gpt-3.5-turbo

    references to online platforms and websites

    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
     Creed
    -0.69
    Weak
    -0.66
     Keystone
    -0.64
    inventoryQuantity
    -0.64
     Decay
    -0.62
    soType
    -0.61
     Ake
    -0.61
    Ak
    -0.61
     Corps
    -0.60
     Advantage
    -0.59
    POSITIVE LOGITS
     guides
    0.99
     listings
    0.93
    information
    0.92
     educate
    0.88
     educating
    0.85
     tutorials
    0.84
     informative
    0.84
    swers
    0.79
    endium
    0.79
     unbiased
    0.79
    Activations Density 0.510%

    No Known Activations