© 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. 14180
    Prev
    Next
    INDEX
    Explanations

    legal and bureaucratic terms

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express conclusions or summaries

    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
     dimensional
    -0.85
     inward
    -0.79
     bullish
    -0.76
     phenomen
    -0.76
     skelet
    -0.76
     overshadow
    -0.76
     aesthetic
    -0.75
     palate
    -0.75
     satell
    -0.74
     butcher
    -0.74
    POSITIVE LOGITS
     Previously
    1.42
     Applic
    1.40
     Individuals
    1.38
     However
    1.35
     Currently
    1.33
     Critics
    1.30
     Anyone
    1.30
     Otherwise
    1.29
    Applic
    1.28
     Therefore
    1.27
    Activations Density 0.411%

    No Known Activations