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. 2411
    Prev
    Next
    INDEX
    Explanations

    details related to animals, particularly capturing, endangered species, and unusual characteristics

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to animals and wildlife, particularly focusing on endangered species and associated risks

    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
    VPN
    -0.90
     Libraries
    -0.87
    Camera
    -0.84
     surgeons
    -0.81
     Shoes
    -0.81
    soType
    -0.79
    Mayor
    -0.79
     Architects
    -0.79
    License
    -0.78
     Parking
    -0.77
    POSITIVE LOGITS
     newly
    1.01
     homegrown
    1.01
     ultra
    0.95
     nascent
    0.92
    ãĤ°
    0.91
     fledgling
    0.90
     new
    0.89
     freshly
    0.87
     domestically
    0.86
     single
    0.84
    Activations Density 0.595%

    No Known Activations