© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8-RES-JB
    11. 14306
    Prev
    Next
    INDEX
    Explanations

    words related to superpowers or special abilities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to abilities and powers, particularly in a fantastical or superhero context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Case
    -0.89
     è£ıè
    -0.84
    review
    -0.80
    Hamilton
    -0.79
    thouse
    -0.79
    ropolitan
    -0.78
    orters
    -0.77
    displayText
    -0.77
    soDeliveryDate
    -0.77
    rolet
    -0.76
    POSITIVE LOGITS
     teleportation
    1.43
     teleport
    1.39
     armor
    1.37
     runes
    1.26
     poisons
    1.26
     armour
    1.23
     Berserker
    1.21
     abilities
    1.20
     mana
    1.18
     sorcery
    1.17
    Activations Density 0.825%

    No Known Activations