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. 7-RES-JB
    6. 22141
    Prev
    Next
    INDEX
    Explanations

    references to characters and concepts from a specific science fiction franchise

    oai_token-act-pair · gpt-3.5-turbo

    references to Jedi and Sith characters from the Star Wars universe

    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
    iard
    -0.77
    ivity
    -0.74
    imen
    -0.71
    esville
    -0.71
     Vog
    -0.70
    iop
    -0.69
    IED
    -0.68
     Ou
    -0.67
     Webster
    -0.66
    Tags
    -0.65
    POSITIVE LOGITS
     Skywalker
    1.12
     Kenobi
    0.92
     Vader
    0.88
     Rebels
    0.85
     lightsaber
    0.82
     Awakens
    0.81
    warm
    0.78
     Trad
    0.76
    ldom
    0.76
    acca
    0.75
    Activations Density 0.074%

    No Known Activations