© 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. 9-RES-JB
    11. 15448
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to specific locations or people

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations and entities related to events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rac
    -0.78
    opian
    -0.76
    culus
    -0.74
    ascus
    -0.71
     linkage
    -0.71
    arg
    -0.70
     saddle
    -0.69
     dynam
    -0.69
     packing
    -0.69
     orbital
    -0.69
    POSITIVE LOGITS
     To
    1.30
     Like
    1.30
     Of
    1.28
     Where
    1.26
     Not
    1.26
     With
    1.25
     Again
    1.25
     Twice
    1.25
     That
    1.24
     Were
    1.24
    Activations Density 0.332%

    No Known Activations