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. 2509
    Prev
    Next
    INDEX
    Explanations

    words related to venues like nightclubs

    oai_token-act-pair · gpt-3.5-turbo
    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
    åĬ
    -0.82
    matter
    -0.72
    ioxide
    -0.72
    ãģĦ
    -0.68
    LOCK
    -0.67
    eded
    -0.66
    ircraft
    -0.66
    20439
    -0.64
     Incarn
    -0.61
    romy
    -0.61
    POSITIVE LOGITS
     frequ
    1.06
     cafes
    1.05
     Royale
    0.95
     cafe
    0.95
     tavern
    0.95
     owner
    0.95
     caf
    0.94
     café
    0.94
     kios
    0.92
     establishments
    0.92
    Activations Density 0.193%

    No Known Activations