© 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. 7-RES-JB
    6. 15291
    Prev
    Next
    INDEX
    Explanations

    names or terms related to various locations and entities

    oai_token-act-pair · gpt-3.5-turbo

    names related to food and beverages, especially those with unusual or playful connotations

    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
     compr
    -0.77
    ccess
    -0.73
     coron
    -0.71
    ascular
    -0.70
     allowable
    -0.69
    ournal
    -0.68
    urable
    -0.67
     clipboard
    -0.67
    alty
    -0.67
     regulator
    -0.67
    POSITIVE LOGITS
    haus
    0.91
    finger
    0.91
    VPN
    0.91
    breaker
    0.87
     Creek
    0.87
     Mile
    0.87
     Shop
    0.86
     Dome
    0.85
     Dogs
    0.85
     Games
    0.84
    Activations Density 0.256%

    No Known Activations