© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 12985
    Prev
    Next
    INDEX
    Explanations

    references to camera specifications, particularly related to megapixels

    oai_token-act-pair · gpt-3.5-turbo

    references to camera specifications and types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ties
    -0.74
     segregation
    -0.72
     occupational
    -0.71
    gaard
    -0.71
    fell
    -0.71
    gren
    -0.69
    stad
    -0.68
    ife
    -0.67
    iott
    -0.66
    neg
    -0.65
    POSITIVE LOGITS
    apixel
    1.32
    ographer
    0.94
    ographers
    0.94
    perture
    0.93
    ographed
    0.91
    illon
    0.88
     JPEG
    0.87
    ography
    0.86
     Fuji
    0.84
    asus
    0.83
    Activations Density 0.023%

    No Known Activations