© 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. 11359
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific points or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific points or markers in various contexts

    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
    uthor
    -0.75
    ÄŁ
    -0.69
     Clause
    -0.67
    ESE
    -0.65
    ther
    -0.65
    NetMessage
    -0.65
    atable
    -0.64
     Sut
    -0.61
    igion
    -0.59
    iband
    -0.59
    POSITIVE LOGITS
    blank
    1.12
     blank
    0.99
    lessly
    0.98
     Reyes
    0.90
    edly
    0.86
     guard
    0.83
     deduction
    0.81
    lessness
    0.79
     deductions
    0.76
    finder
    0.74
    Activations Density 0.057%

    No Known Activations