© 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. 16513
    Prev
    Next
    INDEX
    Explanations

    special characters likely representing hidden or encoded information

    oai_token-act-pair · gpt-3.5-turbo

    the end-of-text token and specific unique or special characters

    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
     scattering
    -0.76
     wink
    -0.74
     gad
    -0.73
     gag
    -0.69
     clad
    -0.68
     casting
    -0.68
     whichever
    -0.68
     scatter
    -0.68
     planting
    -0.68
     Peb
    -0.67
    POSITIVE LOGITS
    º
    1.60
    ¹
    1.47
    Į
    1.41
    į
    1.40
    £
    1.39
    ª
    1.38
    ®
    1.37
    »
    1.37
    ¯
    1.30
    Ń
    1.30
    Activations Density 0.125%

    No Known Activations