© 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. 11-RES-JB
    11. 13651
    Prev
    Next
    INDEX
    Explanations

    phrases related to science fiction and action movies

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks indicating strong conclusions or transitions in the text

    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
     urgent
    -0.74
     democrat
    -0.72
     congest
    -0.66
     affordability
    -0.66
     surging
    -0.66
    ateurs
    -0.65
     scramble
    -0.65
     costly
    -0.65
    uckland
    -0.64
     mindfulness
    -0.64
    POSITIVE LOGITS
    Appearances
    1.36
    Gallery
    1.34
    Trivia
    1.34
    Contents
    1.20
     Played
    1.20
     cameo
    1.16
    episode
    1.14
     flashbacks
    1.13
    Quotes
    1.09
    canon
    1.06
    Activations Density 0.448%

    No Known Activations