© 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. 3378
    Prev
    Next
    INDEX
    Explanations

    examples or instances of something within a broader category

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to examples and notable challenges

    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
    ouls
    -0.76
    pees
    -0.75
    Democrats
    -0.71
    WAR
    -0.69
    autions
    -0.69
    reens
    -0.67
    onds
    -0.66
    roxy
    -0.65
    adoes
    -0.64
     cords
    -0.64
    POSITIVE LOGITS
     example
    1.75
    example
    1.41
     exception
    1.37
     instance
    1.33
     examples
    1.22
     notable
    1.21
    Example
    1.09
     particular
    1.04
     such
    1.03
     Example
    1.02
    Activations Density 0.290%

    No Known Activations