© 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. 3249
    Prev
    Next
    INDEX
    Explanations

    mentions of technology and updates

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" emphasizing its frequency in the context of various topics

    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
     Airl
    -0.65
    hews
    -0.62
    ince
    -0.61
    verbal
    -0.61
     Mechdragon
    -0.60
    dq
    -0.59
     nonviolent
    -0.59
    hoe
    -0.59
    uct
    -0.58
    sighted
    -0.57
    POSITIVE LOGITS
    romeda
    1.06
     congr
    0.97
     therein
    0.90
     congratulations
    0.88
     hopefully
    0.87
     thence
    0.82
     thus
    0.82
     rightfully
    0.80
     luckily
    0.78
     wow
    0.78
    Activations Density 0.307%

    No Known Activations