© 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. 10652
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "aby."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "baby" in various contexts

    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
    ivity
    -0.88
    fully
    -0.75
    iveness
    -0.75
    ively
    -0.71
    imar
    -0.69
    itably
    -0.68
     pity
    -0.68
    encing
    -0.68
    panic
    -0.66
    endiary
    -0.65
    POSITIVE LOGITS
    aby
    0.92
    ħĭ
    0.90
     Isles
    0.77
    stals
    0.75
    azo
    0.74
    acus
    0.72
     Lans
    0.72
    rics
    0.71
    aroo
    0.70
    ertodd
    0.69
    Activations Density 0.016%

    No Known Activations