© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 22628
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific movies, especially those in a particular series

    oai_token-act-pair · gpt-3.5-turbo

    references to movie titles and their sequels

    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
    Not in Any Lists

    No Comments

    Negative Logits
     trough
    -0.77
    hole
    -0.75
     pockets
    -0.73
     misfortune
    -0.72
     negatively
    -0.69
     outp
    -0.68
     fue
    -0.67
     adversely
    -0.67
     worsen
    -0.66
     milit
    -0.65
    POSITIVE LOGITS
     Detail
    0.84
     Intent
    0.84
     Machines
    0.82
     Colossus
    0.80
     Kings
    0.80
     Species
    0.80
     Childhood
    0.79
     Osiris
    0.76
     Cortex
    0.75
     Ancients
    0.74
    Activations Density 0.081%

    No Known Activations