© 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. 9-RES-JB
    11. 5855
    Prev
    Next
    INDEX
    Explanations

    phrases indicating importance, attention, or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the importance or value of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hemor
    -0.65
    ynthesis
    -0.62
    rets
    -0.62
     maneu
    -0.61
     conn
    -0.59
     attrition
    -0.59
     sabot
    -0.58
     Instr
    -0.57
    dimension
    -0.57
     filib
    -0.57
    POSITIVE LOGITS
     nonetheless
    0.92
    \.
    0.87
     considering
    0.82
     because
    0.80
     :)
    0.77
    .*
    0.71
    ographer
    0.70
     :-)
    0.69
     ;)
    0.68
    *.
    0.68
    Activations Density 0.301%

    No Known Activations