© 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. 12-RES-JB
    11. 4522
    Prev
    Next
    INDEX
    Explanations

    religious or spiritual references and prophecies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases related to promises and prophecies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agonists
    -0.94
    ographics
    -0.81
    adas
    -0.81
    pps
    -0.81
    ickets
    -0.81
    okers
    -0.80
    apps
    -0.80
    drivers
    -0.80
    bits
    -0.79
    agues
    -0.79
    POSITIVE LOGITS
     inscription
    1.16
     poem
    1.13
     verse
    1.08
     passage
    1.08
     deed
    1.07
     sublime
    1.06
     sacrament
    1.05
     doctrine
    1.03
     quotation
    1.03
     marvelous
    1.01
    Activations Density 0.277%

    No Known Activations