© 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. 11-RES-JB
    11. 22348
    Prev
    Next
    INDEX
    Explanations

    future-oriented actions or plans

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "will" and its variations indicating future actions or commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quickShipAvailable
    -0.77
    sett
    -0.76
    hea
    -0.76
    minecraft
    -0.69
    BuyableInstoreAndOnline
    -0.68
    MpServer
    -0.68
    ById
    -0.67
    aughs
    -0.67
    stood
    -0.66
    INTON
    -0.66
    POSITIVE LOGITS
     announce
    1.13
     be
    1.08
     unveil
    1.06
     introduce
    1.02
     endeavour
    1.02
     publish
    1.01
     gladly
    0.99
     update
    0.98
     continue
    0.97
     definitely
    0.96
    Activations Density 0.137%

    No Known Activations