© 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. 2241
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies and research publications

    oai_token-act-pair · gpt-3.5-turbo

    references to studies and publications in academic journals

    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
    chwitz
    -0.81
    odka
    -0.73
    orrow
    -0.72
    addon
    -0.71
    gage
    -0.71
     snipers
    -0.69
    crew
    -0.69
    zar
    -0.68
     renting
    -0.68
    iquid
    -0.68
    POSITIVE LOGITS
     Proceedings
    1.36
     PLoS
    1.14
     Scientific
    1.06
    doi
    1.05
     journal
    1.04
     journals
    1.02
     Journal
    0.98
     Pediatrics
    0.96
    published
    0.94
    ournals
    0.92
    Activations Density 0.107%

    No Known Activations