© 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. 14270
    Prev
    Next
    INDEX
    Explanations

    instances of financial or administrative terminology

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and sentence-ending structures

    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
     gobl
    -0.93
     tradem
    -0.87
    plet
    -0.82
     earthqu
    -0.79
     unemploy
    -0.79
    izoph
    -0.76
    emort
    -0.76
     millenn
    -0.75
    ŃĶ
    -0.75
     citiz
    -0.74
    POSITIVE LOGITS
     Consequently
    1.56
     Therefore
    1.53
     Thus
    1.45
     Hence
    1.45
     Accordingly
    1.45
     However
    1.43
     But
    1.37
     Typically
    1.35
     Whereas
    1.32
     Conversely
    1.30
    Activations Density 0.461%

    No Known Activations