© 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. 4-RES-JB
    11. 1829
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences indicating a task or situation that is challenging or difficult to navigate

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "tricky" and its related terms, indicating challenging situations

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

    No Comments

    Negative Logits
    oration
    -0.88
    ablishment
    -0.85
    owment
    -0.78
    arer
    -0.70
    ember
    -0.70
    alsh
    -0.70
    vation
    -0.70
    onde
    -0.69
    ablish
    -0.69
    ental
    -0.67
    POSITIVE LOGITS
     tricky
    1.12
     little
    0.78
     knot
    0.77
     pesky
    0.77
     delicate
    0.73
     trig
    0.72
     forgiving
    0.71
     juggling
    0.69
     navigating
    0.68
     conce
    0.68
    Activations Density 0.015%

    No Known Activations