© 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. 0-RES-JB
    11. 13200
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to 'scared' or fear

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word 'ared' in various contexts

    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
     Ess
    -0.69
     restoration
    -0.60
     Ars
    -0.60
     renov
    -0.59
     usher
    -0.59
     Du
    -0.58
     corrections
    -0.58
     Goodman
    -0.58
     speculation
    -0.57
     defect
    -0.56
    POSITIVE LOGITS
    ared
    4.59
    aring
    2.64
    ares
    2.25
    arer
    1.85
    are
    1.61
    ars
    1.59
    arers
    1.54
    ARE
    1.31
    athed
    1.24
    aped
    1.21
    Activations Density 0.007%

    No Known Activations