© 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. 9603
    Prev
    Next
    INDEX
    Explanations

    specific phrases or snippets of information related to a variety of topics or events

    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
    ãĥĺ
    -0.89
    aneers
    -0.82
    ãĥł
    -0.80
    ¨
    -0.79
    rued
    -0.76
    gas
    -0.73
    alties
    -0.72
    Disk
    -0.71
    lees
    -0.70
    FontSize
    -0.68
    POSITIVE LOGITS
     rundown
    0.95
     synopsis
    0.91
     excerpt
    0.89
     overview
    0.86
     breakdown
    0.85
     tentative
    0.83
     summary
    0.78
     preliminary
    0.77
     caveat
    0.76
     kicker
    0.75
    Activations Density 0.078%

    No Known Activations