© 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. 12167
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to equipment, tools, and maneuvers in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    descriptions or attributes related to complexity and strategy in contexts such as games or navigational challenges

    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
     Politics
    -0.66
    soType
    -0.65
     Funding
    -0.62
     Emails
    -0.62
    ????????
    -0.61
     redacted
    -0.60
     Shit
    -0.59
    Wait
    -0.59
     Months
    -0.58
     Godd
    -0.58
    POSITIVE LOGITS
     excel
    1.04
     optimum
    1.00
     proficient
    0.98
     adept
    0.94
     advantageous
    0.91
     suitable
    0.91
     util
    0.90
     suited
    0.90
     exce
    0.90
     difficulty
    0.89
    Activations Density 0.691%

    No Known Activations