© 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 EvalsExportsinterp-engineNEWAPI 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. 18917
    Prev
    Next
    INDEX
    Explanations

    entities or titles identified by the symbol "Ċ"

    oai_token-act-pair · gpt-3.5-turbo

    discrete numerical data and references to specific entities or events

    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
     veter
    -0.74
     hiber
    -0.67
     dating
    -0.67
     allied
    -0.64
     capit
    -0.63
     shoulders
    -0.63
     imperson
    -0.63
     volunt
    -0.61
     wrists
    -0.61
     chairs
    -0.61
    POSITIVE LOGITS
    Imagine
    0.82
    ILLE
    0.82
    ³³³³³³³³³³³³³³³³
    0.82
    Photo
    0.81
    Express
    0.80
    verett
    0.79
    ³³³³
    0.77
    GREEN
    0.77
    ³³³
    0.76
    photo
    0.76
    Activations Density 0.203%

    No Known Activations