© 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. 8-RES-JB
    11. 17193
    Prev
    Next
    INDEX
    Explanations

    proper names of people

    oai_token-act-pair · gpt-3.5-turbo

    references to news sources and journalists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Conquer
    -0.66
     Ideal
    -0.64
    Sold
    -0.62
    isters
    -0.62
    Offic
    -0.60
     Ministers
    -0.60
     Fortress
    -0.59
    Scotland
    -0.59
    bitious
    -0.59
    patient
    -0.58
    POSITIVE LOGITS
     (@
    0.99
     tweeted
    0.91
     Jr
    0.89
    iott
    0.85
     headlined
    0.84
     contributed
    0.83
     alerted
    0.80
     wrote
    0.79
     wondered
    0.79
    witz
    0.78
    Activations Density 0.180%

    No Known Activations