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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11711
    Prev
    Next
    INDEX
    Explanations

    verbs related to future actions or plans

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating future events or expectations

    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
    heit
    -0.77
    Express
    -0.66
    bach
    -0.64
    bart
    -0.61
    how
    -0.60
    Simply
    -0.60
    hett
    -0.60
    oyal
    -0.58
     forgetting
    -0.58
    pmwiki
    -0.58
    POSITIVE LOGITS
     sometime
    1.06
     soon
    1.02
     someday
    0.83
     sooner
    0.79
     next
    0.75
     anytime
    0.73
     shortly
    0.68
     further
    0.64
     tomorrow
    0.64
     2020
    0.63
    Activations Density 0.373%

    No Known Activations