© 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. 10-RES-JB
    11. 10377
    Prev
    Next
    INDEX
    Explanations

    features, characteristics, or specifications of different products

    oai_token-act-pair · gpt-3.5-turbo

    conjunction words and their relationships in descriptions

    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
    anmar
    -0.80
    Were
    -0.78
    estern
    -0.70
    untled
    -0.70
    actionDate
    -0.69
    çIJ
    -0.68
    psey
    -0.68
    onica
    -0.66
    atars
    -0.65
    ntil
    -0.65
    POSITIVE LOGITS
     provides
    1.80
     contains
    1.72
     incorporates
    1.71
     integrates
    1.71
     allows
    1.71
     produces
    1.71
     protects
    1.68
     maintains
    1.68
     relies
    1.67
     contributes
    1.67
    Activations Density 0.432%

    No Known Activations