© 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. 0-RES-JB
    11. 1368
    Prev
    Next
    INDEX
    Explanations

    phrases expressing future events

    oai_token-act-pair · gpt-3.5-turbo

    future predictions or assertions of intention

    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
    zai
    -0.67
    agascar
    -0.64
    Abstract
    -0.63
    olulu
    -0.61
    uously
    -0.59
    VERTIS
    -0.59
    herent
    -0.59
    itaire
    -0.58
    ausible
    -0.57
    occupied
    -0.56
    POSITIVE LOGITS
     will
    2.74
    will
    2.17
     WILL
    2.02
    'll
    1.93
     shall
    1.66
    Will
    1.64
     Will
    1.62
     SHALL
    1.53
     wont
    1.51
     won
    1.45
    Activations Density 0.166%

    No Known Activations