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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 20049
    Prev
    Next
    INDEX
    Explanations

    names of characters or actors playing characters in films

    oai_token-act-pair · gpt-3.5-turbo

    references to notable film characters and their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istries
    -1.07
    AMS
    -0.93
    ournals
    -0.89
    views
    -0.89
    ICES
    -0.87
    atories
    -0.87
    orders
    -0.85
    ISO
    -0.84
    Apps
    -0.84
    tests
    -0.84
    POSITIVE LOGITS
     protagonist
    1.29
     narrator
    1.26
     bearded
    1.26
     villain
    1.26
     guy
    1.24
     heroine
    1.17
     handsome
    1.17
     blonde
    1.17
     blond
    1.13
     thief
    1.13
    Activations Density 0.326%

    No Known Activations