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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 4056
    Prev
    Next
    INDEX
    Explanations

    keywords related to uploading content, particularly images and files, to online platforms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to uploading and sharing content online

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cantor
    -0.78
     TRE
    -0.72
    sym
    -0.70
    lie
    -0.69
     Continental
    -0.68
     dime
    -0.68
     Treasury
    -0.68
     Greek
    -0.65
     Corinthians
    -0.64
     Leading
    -0.64
    POSITIVE LOGITS
     upload
    3.59
     uploading
    3.09
     uploaded
    2.96
     Upload
    2.75
    Upload
    2.63
    upload
    2.58
    uploads
    1.75
     download
    1.48
     downloads
    1.40
     downloading
    1.39
    Activations Density 0.011%

    No Known Activations