© 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. 10-RES-JB
    11. 17497
    Prev
    Next
    INDEX
    Explanations

    mentions of ongoing discussions and unknown aspects within a given context

    oai_token-act-pair · gpt-3.5-turbo

    discussions focused on ongoing research or unknown aspects within a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shutdown
    -0.88
     Bucket
    -0.78
    minus
    -0.77
     Oath
    -0.75
     Ruler
    -0.75
    gencies
    -0.75
     Destination
    -0.72
    Gov
    -0.72
    Exit
    -0.72
     Streets
    -0.72
    POSITIVE LOGITS
     literature
    1.57
     studies
    1.47
     empirical
    1.36
     research
    1.35
     observational
    1.33
     methodological
    1.33
     scientific
    1.32
     scholarly
    1.32
     neuroscience
    1.31
     epidem
    1.22
    Activations Density 0.495%

    No Known Activations