© 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. 8-RES-JB
    11. 2417
    Prev
    Next
    INDEX
    Explanations

    quip-related actions and statements

    oai_token-act-pair · gpt-3.5-turbo

    informal speech or expressions of humor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.71
    iris
    -0.67
    establishment
    -0.67
    ãĥ¯
    -0.67
    Copy
    -0.65
    ovo
    -0.65
    ãĥ¼ãĥ«
    -0.63
    AMY
    -0.63
    arrow
    -0.62
    keys
    -0.62
    POSITIVE LOGITS
     aloud
    1.41
     loudly
    1.08
     about
    1.03
     sarcast
    0.97
     bitterly
    0.96
     endlessly
    0.94
     nostalg
    0.94
     confidently
    0.92
     ABOUT
    0.90
     angrily
    0.81
    Activations Density 0.163%

    No Known Activations