© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 14324
    Prev
    Next
    INDEX
    Explanations

    phrases related to fear and threats

    oai_token-act-pair · gpt-3.5-turbo

    references to anxiety and emotional responses to various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 11 - fear

    No Comments

    Negative Logits
    cellence
    -0.78
    Iterator
    -0.78
    OGR
    -0.76
     Gibbs
    -0.74
     Collections
    -0.74
     Beans
    -0.72
     Transfer
    -0.72
     Efficiency
    -0.71
     Abram
    -0.70
    utenberg
    -0.70
    POSITIVE LOGITS
     fear
    1.99
     fears
    1.87
     scares
    1.78
     scare
    1.69
    Fear
    1.68
     fearful
    1.65
     Fear
    1.63
     scared
    1.61
     worry
    1.61
     scary
    1.61
    Activations Density 0.603%

    No Known Activations