© 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. 10095
    Prev
    Next
    INDEX
    Explanations

    phrases related to asking questions or expressing uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of various contractions

    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
     Pru
    -0.68
    manship
    -0.65
     agre
    -0.61
    rador
    -0.59
    İĭ
    -0.59
     answ
    -0.58
     ende
    -0.58
    conservancy
    -0.58
     interf
    -0.58
     rematch
    -0.57
    POSITIVE LOGITS
    Allah
    0.92
    Brien
    0.81
    Mech
    0.78
    thur
    0.77
    bor
    0.76
    Cause
    0.76
    Malley
    0.75
    Donnell
    0.75
    arak
    0.72
    TB
    0.71
    Activations Density 0.041%

    No Known Activations