© 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. 23081
    Prev
    Next
    INDEX
    Explanations

    web URLs that begin with the number 2

    oai_token-act-pair · gpt-3.5-turbo

    references to numbers and numeric identifiers

    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
    by
    -0.52
    itan
    -0.51
    ance
    -0.50
    ides
    -0.50
    sted
    -0.49
    utive
    -0.47
     disapp
    -0.45
    ologies
    -0.45
     Dign
    -0.45
     Duck
    -0.45
    POSITIVE LOGITS
    yss
    0.68
    hari
    0.65
    eh
    0.65
    HER
    0.64
    fman
    0.64
    ech
    0.62
    eri
    0.59
    hovah
    0.59
    20439
    0.58
    eches
    0.58
    Activations Density 0.231%

    No Known Activations