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. 9-RES-JB
    6. 21682
    Prev
    Next
    INDEX
    Explanations

    mentions of events, locations, and dates in a structured format

    oai_token-act-pair · gpt-3.5-turbo

    structured information related to time and location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hiber
    -0.79
     paralle
    -0.76
     spinning
    -0.75
     spir
    -0.74
     differe
    -0.74
     dab
    -0.74
     bol
    -0.73
     tightening
    -0.73
     spiral
    -0.72
     glowing
    -0.72
    POSITIVE LOGITS
    Status
    1.46
    Duration
    1.43
    Publisher
    1.34
    Location
    1.33
    Country
    1.33
    Synopsis
    1.31
    Subject
    1.29
    Rating
    1.28
    Population
    1.28
    Label
    1.27
    Activations Density 0.182%

    No Known Activations