© 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. 7-RES-JB
    11. 5364
    Prev
    Next
    INDEX
    Explanations

    references to splash screens

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "splash" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    elsen
    -0.82
    ollower
    -0.74
    algia
    -0.74
    alties
    -0.69
    usable
    -0.69
    rals
    -0.69
    hart
    -0.67
    asons
    -0.67
    abiding
    -0.66
    Wan
    -0.65
    POSITIVE LOGITS
     splash
    0.89
     Splash
    0.83
     Mehran
    0.77
    lihood
    0.70
     graffiti
    0.66
     Alley
    0.65
    bytes
    0.64
    down
    0.62
     dunk
    0.61
     TBA
    0.61
    Activations Density 0.054%

    No Known Activations