© 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. 5000
    Prev
    Next
    INDEX
    Explanations

    incremental steps in numerical values, possibly related to measurements or ratings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "us" in various contexts

    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
    RAG
    -0.71
     td
    -0.64
    ottest
    -0.61
    ITNESS
    -0.60
    rought
    -0.57
     reservations
    -0.56
    ested
    -0.55
    irst
    -0.55
    owler
    -0.54
     payday
    -0.54
    POSITIVE LOGITS
    pex
    1.24
    CRIP
    1.15
    chwitz
    1.14
    cular
    1.09
    peed
    1.01
    cules
    1.01
    sein
    1.01
    etts
    0.99
    henko
    0.97
    cul
    0.96
    Activations Density 0.076%

    No Known Activations