© 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. 4390
    Prev
    Next
    INDEX
    Explanations

    lists of names of notable people and movies

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

    references to notable filmmakers and their cinematic works

    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
     listeners
    -0.77
     notation
    -0.76
     fundament
    -0.69
     voc
    -0.68
    ento
    -0.66
     differe
    -0.66
     trough
    -0.65
     opin
    -0.65
     rhet
    -0.65
    ande
    -0.63
    POSITIVE LOGITS
     Gladiator
    1.15
     Beasts
    1.10
     Titanic
    1.10
     Parenthood
    1.09
     Taxi
    1.08
     Interstellar
    1.08
     Terminator
    1.07
     Jurassic
    1.06
     Finding
    1.05
     Transformers
    1.04
    Activations Density 0.241%

    No Known Activations