© 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. 11-RES-JB
    11. 22433
    Prev
    Next
    INDEX
    Explanations

    instances of first-person perspective descriptions or references

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "first-person" perspectives and narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DAY
    -0.87
    bats
    -0.83
    sung
    -0.78
    kil
    -0.78
    protect
    -0.77
    pload
    -0.76
    TAG
    -0.73
    thirst
    -0.71
    disk
    -0.69
    GUI
    -0.69
    POSITIVE LOGITS
    endment
    0.75
    erers
    0.73
     foremost
    0.69
     missionary
    0.69
     perspective
    0.68
    imester
    0.68
     citizenship
    0.64
     accuser
    0.62
     vantage
    0.62
     plural
    0.62
    Activations Density 0.148%

    No Known Activations