© 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. 10-RES-JB
    11. 18556
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a transition into a specific phase or state

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to transitions and new phases, particularly in the context of careers or important events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ensical
    -0.66
    eka
    -0.66
    vich
    -0.61
     hurled
    -0.58
     constitu
    -0.58
    cu
    -0.57
    inet
    -0.57
    ousing
    -0.57
    found
    -0.57
    quartered
    -0.56
    POSITIVE LOGITS
     adulthood
    1.23
     2017
    1.07
     adolescence
    1.04
     2018
    0.99
     2019
    0.99
     twilight
    0.97
     offseason
    0.96
     2020
    0.95
     Year
    0.94
     halftime
    0.93
    Activations Density 0.133%

    No Known Activations