© 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. 9-RES-JB
    11. 15488
    Prev
    Next
    INDEX
    Explanations

    dates formatted as Month-Day, Year

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks or special characters that indicate sentence boundaries or sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     outwe
    -0.84
    ube
    -0.78
     behav
    -0.75
     minded
    -0.73
    matically
    -0.73
    beh
    -0.71
     past
    -0.70
    entimes
    -0.66
    onite
    -0.65
    lly
    -0.65
    POSITIVE LOGITS
     Begins
    0.91
     Ferry
    0.90
     Recap
    0.88
     Started
    0.86
     Announce
    0.86
     Starts
    0.84
     Released
    0.84
     Converted
    0.83
     Newly
    0.83
     Introdu
    0.83
    Activations Density 0.146%

    No Known Activations