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. 11-RES-JB
    6. 19050
    Prev
    Next
    INDEX
    Explanations

    mentions of camera brands and features

    oai_token-act-pair · gpt-3.5-turbo

    mentions of camera brands and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soType
    -0.90
    ŃĶ
    -0.85
     Satanic
    -0.79
     Corker
    -0.79
     Randolph
    -0.78
    atchewan
    -0.77
    Dun
    -0.77
    nesota
    -0.76
     Mattis
    -0.76
    MpServer
    -0.75
    POSITIVE LOGITS
     Nikon
    1.89
     Camera
    1.79
     Leica
    1.79
     camera
    1.78
     shutter
    1.74
    Camera
    1.71
    camera
    1.71
     Canon
    1.66
     photography
    1.65
     cameras
    1.63
    Activations Density 0.443%

    No Known Activations