© 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. 1-RES-JB
    11. 3859
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of structure, either physical or social

    oai_token-act-pair · gpt-3.5-turbo

    words related to structural and cultural significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ials
    -0.71
     Riders
    -0.70
     Express
    -0.69
     Delivery
    -0.68
    ger
    -0.66
    gers
    -0.65
     HERO
    -0.64
     Channel
    -0.64
    ties
    -0.64
    raviolet
    -0.63
    POSITIVE LOGITS
    urally
    1.14
    psey
    0.95
     pleasing
    0.88
     conduc
    0.83
     regenerate
    0.81
     exting
    0.80
     distingu
    0.79
    hematically
    0.78
     compr
    0.76
    bane
    0.76
    Activations Density 0.016%

    No Known Activations