© 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. 5918
    Prev
    Next
    INDEX
    Explanations

    texts separated by a specific character 'Ċ'

    oai_token-act-pair · gpt-3.5-turbo

    expressions of confusion or uncertainty

    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
     citiz
    -0.83
     wearer
    -0.69
     tremend
    -0.68
    cius
    -0.68
     eleph
    -0.67
     Skydragon
    -0.66
    £ı
    -0.64
    senal
    -0.63
     newcom
    -0.62
    lihood
    -0.62
    POSITIVE LOGITS
    ↵
    0.69
    OD
    0.66
    Db
    0.62
    arte
    0.62
    Els
    0.62
    ORD
    0.62
    amps
    0.60
    amp
    0.60
    orm
    0.58
    Med
    0.57
    Activations Density 0.457%

    No Known Activations