© 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. 11-RES-JB
    11. 20890
    Prev
    Next
    INDEX
    Explanations

    phrases related to predictions or commitments

    oai_token-act-pair · gpt-3.5-turbo

    the repeated character sequence 'Ļ' and possibly related patterns or forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chattanooga
    -0.62
     Brook
    -0.55
    undown
    -0.54
     Targ
    -0.54
     Robin
    -0.53
     Barkley
    -0.53
    jon
    -0.53
     Rocket
    -0.52
    Rocket
    -0.51
     Yor
    -0.51
    POSITIVE LOGITS
    ¹
    0.86
    ·
    0.85
    ulty
    0.83
    ¯¯
    0.80
    ¯
    0.79
    ems
    0.78
    ves
    0.77
    ķ
    0.76
    ¢
    0.75
    º
    0.73
    Activations Density 0.259%

    No Known Activations