© 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 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. 4194
    Prev
    Next
    INDEX
    Explanations

    phrases indicating difficulty or challenge

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing difficulty or challenges

    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
    ellig
    -0.73
    psc
    -0.72
    ificantly
    -0.71
    bnb
    -0.71
    ibraries
    -0.69
    ifest
    -0.68
    ortium
    -0.68
    ongh
    -0.66
    vironment
    -0.66
    ucer
    -0.66
    POSITIVE LOGITS
     slog
    1.02
     navigating
    0.99
     daunting
    0.90
     uphill
    0.88
     figuring
    0.86
     hurdle
    0.86
     climb
    0.86
     juggling
    0.85
     ardu
    0.84
     childbirth
    0.83
    Activations Density 0.367%

    No Known Activations