Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 14893
    Prev
    Next
    INDEX
    Explanations

    phrases related to movie titles and character names from the Star Wars franchise

    oai_token-act-pair · gpt-3.5-turbo

    titles or elements related to the Star Wars franchise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ£
    -0.52
    omorphic
    -0.51
     calendars
    -0.50
     cour
    -0.47
     coh
    -0.46
     neut
    -0.46
     bleach
    -0.45
     deaf
    -0.45
     fuzz
    -0.45
     acron
    -0.45
    POSITIVE LOGITS
    ignty
    0.56
    oker
    0.53
    worthiness
    0.52
    ioxide
    0.52
    venge
    0.50
     Azerb
    0.50
    nova
    0.47
    kowski
    0.47
    olesterol
    0.46
    arrow
    0.46
    Activations Density 1.316%

    No Known Activations