© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 3290
    Prev
    Next
    INDEX
    Explanations

    phrases related to news articles or journalistic content

    oai_token-act-pair · gpt-3.5-turbo

    numerals and references to space or significant scientific concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ventus
    -0.75
     ensu
    -0.71
     endeavour
    -0.69
    âĢIJ
    -0.68
     ageing
    -0.67
     inval
    -0.66
     util
    -0.65
     appell
    -0.65
    cules
    -0.64
    JP
    -0.63
    POSITIVE LOGITS
    toggle
    1.23
    Enlarge
    1.18
    NPR
    1.15
     NPR
    1.06
    Interview
    0.78
     Fargo
    0.63
    enegger
    0.61
    .,"
    0.60
    YouTube
    0.58
    ↵
    0.58
    Activations Density 0.068%

    No Known Activations