© 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. 7-RES-JB
    11. 1501
    Prev
    Next
    INDEX
    Explanations

    dates and numbers in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    references to mixed media and related artistic expressions

    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
     oun
    -0.79
    tsky
    -0.76
     XIII
    -0.74
     Bout
    -0.73
     Advantage
    -0.72
     Strongh
    -0.68
     Chair
    -0.68
     Dek
    -0.68
     Bros
    -0.67
     Bark
    -0.66
    POSITIVE LOGITS
    database
    0.87
    natureconservancy
    0.69
    protection
    0.68
    internet
    0.68
    headers
    0.68
    reference
    0.67
    interface
    0.66
    dragon
    0.66
    âĨĴ
    0.66
    google
    0.66
    Activations Density 0.262%

    No Known Activations