© 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. 7-RES-JB
    11. 24541
    Prev
    Next
    INDEX
    Explanations

    pop culture references, particularly titles and names of movies, shows, and books

    oai_token-act-pair · gpt-3.5-turbo

    titles and references to creative works, specifically sequels and movies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UC
    -0.76
    tur
    -0.68
    HC
    -0.67
    549
    -0.66
    otos
    -0.64
    478
    -0.64
    tc
    -0.63
    stim
    -0.62
    compan
    -0.60
    Southern
    -0.60
    POSITIVE LOGITS
     Thrones
    0.91
    aundering
    0.72
    Ħ¢
    0.70
    rage
    0.70
     Sabha
    0.68
     Fortune
    0.66
     Roses
    0.66
    ield
    0.65
    phies
    0.65
     Devices
    0.63
    Activations Density 0.160%

    No Known Activations