© 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. 6-RES-JB
    11. 1522
    Prev
    Next
    INDEX
    Explanations

    the word "to" followed by an action verb

    oai_token-act-pair · gpt-3.5-turbo

    phrases that imply obligation or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Respons
    -0.74
    Friend
    -0.73
     Glad
    -0.71
    Recommended
    -0.70
    Ind
    -0.68
    pires
    -0.65
    quickShipAvailable
    -0.64
    thumbnails
    -0.63
    Mem
    -0.63
    Mur
    -0.63
    POSITIVE LOGITS
     wait
    1.10
     rethink
    1.04
     rely
    0.92
     endure
    0.92
     revise
    0.92
     settle
    0.90
     reconsider
    0.88
     overcome
    0.87
     abide
    0.87
     revisit
    0.87
    Activations Density 0.068%

    No Known Activations