© 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
    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. 16790
    Prev
    Next
    INDEX
    Explanations

    mentions of titles or subtitles containing the phrase "Strikes Back"

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Star Wars" franchise, particularly the phrase "Strikes Back"

    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
     Hannity
    -0.79
     Hilbert
    -0.75
    onna
    -0.68
    folio
    -0.64
     Ana
    -0.63
    bia
    -0.61
     Sioux
    -0.60
     Indra
    -0.59
    iffin
    -0.58
     Overwatch
    -0.57
    POSITIVE LOGITS
     Strikes
    3.74
    Scope
    0.82
     Alger
    0.82
     Chains
    0.79
    âĦ¢:
    0.79
     Runs
    0.79
     McF
    0.79
    llor
    0.78
     Territories
    0.75
     Contracts
    0.75
    Activations Density 0.017%

    No Known Activations