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. 0-RES-JB
    6. 16215
    Prev
    Next
    INDEX
    Explanations

    references to a specific movie title and related terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the "Star Wars: Revenge of the Sith" theme

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arp
    -0.74
     handic
    -0.72
     overest
    -0.69
    opt
    -0.66
    #$
    -0.65
     peg
    -0.65
     Osw
    -0.64
     drift
    -0.62
     opt
    -0.62
     Kelley
    -0.62
    POSITIVE LOGITS
     Revenge
    2.55
     Chronicles
    1.77
    vous
    1.61
     Bold
    1.52
     Curse
    1.40
    venge
    1.30
    bite
    1.25
    urrection
    1.22
    aye
    1.20
     Rebellion
    1.18
    Activations Density 0.062%

    No Known Activations