© 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. 21064
    Prev
    Next
    INDEX
    Explanations

    phrases related to various issues and events, particularly involving organizations or authorities

    oai_token-act-pair · gpt-3.5-turbo

    keywords indicating issues or challenges faced by organizations or systems

    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
    Aw
    -0.71
     pic
    -0.70
     Amen
    -0.68
     sqor
    -0.64
    ðŁ
    -0.62
    âĺ
    -0.61
     cheers
    -0.61
    Yep
    -0.59
     cheering
    -0.59
    tainment
    -0.59
    POSITIVE LOGITS
     undertook
    1.24
     opted
    1.24
     resorted
    1.23
     reverted
    1.22
     realised
    1.21
     attempted
    1.19
     decided
    1.14
     discontinued
    1.12
     experimented
    1.12
     utilized
    1.11
    Activations Density 0.506%

    No Known Activations