© 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. 2-RES-JB
    11. 13643
    Prev
    Next
    INDEX
    Explanations

    terms related to something cherished or admired

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "beloved" and its variations, indicating fondness or affection towards subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramid
    -0.76
    agnetic
    -0.75
    enei
    -0.73
    DoS
    -0.69
    ulhu
    -0.69
    agher
    -0.69
    uid
    -0.69
    cha
    -0.68
    ureau
    -0.67
    techn
    -0.67
    POSITIVE LOGITS
     beloved
    0.87
     dearly
    0.86
     Favorite
    0.75
     loved
    0.71
     darling
    0.71
     cherished
    0.67
     favourite
    0.65
     Friends
    0.63
     pets
    0.63
    lihood
    0.63
    Activations Density 0.010%

    No Known Activations