© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 1811
    Prev
    Next
    INDEX
    Explanations

    adjectives related to confusion or difficulty

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "bewilder" and related expressions indicating confusion or amazement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     appropriated
    -0.82
    inances
    -0.81
    ©¶æ
    -0.75
    cript
    -0.75
    criptions
    -0.74
    available
    -0.74
    ensor
    -0.73
    cribed
    -0.73
    uties
    -0.69
     designated
    -0.66
    POSITIVE LOGITS
    NESS
    0.90
    LY
    0.89
    ness
    0.82
    ly
    0.81
     unbeliev
    0.81
    nesses
    0.80
    ingly
    0.79
     surpr
    0.77
     Beir
    0.76
     boredom
    0.73
    Activations Density 0.142%

    No Known Activations