© 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. 1-RES-JB
    11. 3362
    Prev
    Next
    INDEX
    Explanations

    words related to a specific location or person, specifically the word "Sel"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the term "Sel" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemTracker
    -0.85
    EEE
    -0.70
     FAT
    -0.66
    FG
    -0.66
     Fairfax
    -0.65
    erella
    -0.64
    ALLY
    -0.64
    unct
    -0.63
     HIP
    -0.61
     CPC
    -0.61
    POSITIVE LOGITS
     Sel
    1.04
    Sel
    0.96
     oath
    0.91
    beck
    0.91
    anguage
    0.88
    stones
    0.84
    bum
    0.82
     gobl
    0.81
    enium
    0.80
    inker
    0.80
    Activations Density 0.003%

    No Known Activations