© 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. 11-RES-JB
    11. 20583
    Prev
    Next
    INDEX
    Explanations

    words related to numbers and technical details

    oai_token-act-pair · gpt-3.5-turbo

    specific technical or structured terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ynthesis
    -0.81
    enance
    -0.72
    rium
    -0.71
    cale
    -0.70
    hip
    -0.68
     Written
    -0.67
    urden
    -0.66
    uana
    -0.65
    brance
    -0.65
    ENCE
    -0.63
    POSITIVE LOGITS
     categories
    1.11
     types
    1.10
     slots
    1.09
     scenarios
    1.04
     variants
    1.04
     sites
    1.02
     varieties
    1.01
     configurations
    1.00
     locations
    0.99
     equivalents
    0.97
    Activations Density 0.457%

    No Known Activations