© 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. 4-RES-JB
    11. 17062
    Prev
    Next
    INDEX
    Explanations

    phrases related to moving on or progressing forward

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "move on."

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

    No Comments

    Negative Logits
    BIP
    -0.68
    ptives
    -0.62
    OTH
    -0.61
    YP
    -0.61
    ACT
    -0.60
    Apps
    -0.59
    Ĥª
    -0.59
    SHARE
    -0.59
    Allah
    -0.58
    Po
    -0.57
    POSITIVE LOGITS
     behalf
    1.12
    shore
    1.12
    erous
    1.00
    yx
    0.95
    eday
    0.89
     occasion
    0.89
    sets
    0.87
    eness
    0.85
    site
    0.82
    etime
    0.79
    Activations Density 0.127%

    No Known Activations