© 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. 11765
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating importance or necessity

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating importance or necessity

    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
    DragonMagazine
    -1.04
    Ali
    -0.68
    Aud
    -0.67
     borrowed
    -0.66
     TBA
    -0.65
     hairs
    -0.62
     Malf
    -0.62
    ukemia
    -0.61
     lashes
    -0.61
    balls
    -0.60
    POSITIVE LOGITS
     determining
    1.02
     preserving
    0.94
     sustaining
    0.93
     unlocking
    0.91
     solving
    0.90
     ensuring
    0.87
     maintaining
    0.87
     constructing
    0.85
     achieving
    0.84
     shaping
    0.82
    Activations Density 0.134%

    No Known Activations