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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 634
    Prev
    Next
    INDEX
    Explanations

    words related to fear, anxiety, or negative emotions

    oai_token-act-pair · gpt-3.5-turbo

    references to fear-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 0 - fear

    No Comments

    Negative Logits
     decoration
    -0.73
     lat
    -0.71
     delivery
    -0.70
     operation
    -0.69
     smooth
    -0.69
    insky
    -0.69
     payment
    -0.67
     cler
    -0.67
     components
    -0.67
     transition
    -0.66
    POSITIVE LOGITS
     Fear
    3.66
    Fear
    2.59
     Anger
    1.54
     Panic
    1.36
     Anxiety
    1.28
     Rage
    1.26
     Scream
    1.19
     Courage
    1.19
     Hate
    1.19
     Scare
    1.18
    Activations Density 0.016%

    No Known Activations