© 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. 20934
    Prev
    Next
    INDEX
    Explanations

    phrases expressing fear or concern

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating possibilities or uncertainties

    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
    Dur
    -0.72
    Works
    -0.72
    raq
    -0.68
    Favorite
    -0.67
     Excellent
    -0.67
    AMA
    -0.66
    Excellent
    -0.66
    DAQ
    -0.66
    Awesome
    -0.66
     Rated
    -0.64
    POSITIVE LOGITS
     contam
    1.32
     endanger
    1.21
     undermine
    1.19
     impede
    1.19
     interfere
    1.19
     violate
    1.17
     expose
    1.16
     injure
    1.16
     inadvertently
    1.14
     incite
    1.14
    Activations Density 0.138%

    No Known Activations