© 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. 0-RES-JB
    6. 2578
    Prev
    Next
    INDEX
    Explanations

    items or objects related to sets or collections

    oai_token-act-pair · gpt-3.5-turbo

    references to kits or collections of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Presidents
    -0.69
     SHARES
    -0.68
    among
    -0.68
    rences
    -0.66
     Employees
    -0.66
    agements
    -0.63
    licts
    -0.63
    unct
    -0.62
     cardinal
    -0.62
    azes
    -0.61
    POSITIVE LOGITS
     kit
    3.94
     kits
    3.07
     Kit
    2.41
    kit
    2.02
     Kits
    1.94
    Kit
    1.54
     gear
    1.23
     package
    1.09
     arsenal
    1.06
     pack
    0.99
    Activations Density 0.007%

    No Known Activations