© 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. 6-RES-JB
    11. 15549
    Prev
    Next
    INDEX
    Explanations

    words related to prominent political figures

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rm
    -0.69
     guiName
    -0.66
    owe
    -0.63
     Reported
    -0.63
    ._
    -0.62
    tsky
    -0.62
    RM
    -0.62
    ight
    -0.61
    NetMessage
    -0.58
     (*
    -0.58
    POSITIVE LOGITS
     etc
    1.23
    etc
    1.17
    whatever
    0.92
    ĪĴ
    0.74
    76561
    0.72
    FontSize
    0.69
    åĤ
    0.67
     assorted
    0.64
     carbohyd
    0.61
    govtrack
    0.61
    Activations Density 0.237%

    No Known Activations