© 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. 8-RES-JB
    11. 9441
    Prev
    Next
    INDEX
    Explanations

    phrases related to moving on or transitioning from a situation

    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 @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    °
    -0.75
    ª
    -0.71
    ©
    -0.71
    RL
    -0.70
    OTS
    -0.67
    NK
    -0.67
    ãĥķãĤ¡
    -0.66
     Accessed
    -0.66
    aughtered
    -0.65
    Ķ
    -0.63
    POSITIVE LOGITS
    eday
    0.94
    stage
    0.87
    shore
    0.84
    erous
    0.83
     behalf
    0.82
     stage
    0.81
     fumes
    0.74
     unnoticed
    0.70
     arrival
    0.70
     board
    0.68
    Activations Density 0.051%

    No Known Activations