© 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. 3122
    Prev
    Next
    INDEX
    Explanations

    the word "Allen"

    oai_token-act-pair · gpt-3.5-turbo
    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
    kered
    -0.94
    ulates
    -0.91
    ornia
    -0.90
    ceed
    -0.87
    anooga
    -0.85
    ulate
    -0.83
    */(
    -0.83
    pload
    -0.82
    ounty
    -0.78
    pter
    -0.78
    POSITIVE LOGITS
     Dull
    1.03
     Gins
    0.98
     Allen
    0.82
     Robinson
    0.81
    ham
    0.76
    stown
    0.76
    hurst
    0.72
    heim
    0.71
    quist
    0.70
     Poe
    0.70
    Activations Density 0.027%

    No Known Activations