© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17759
    Prev
    Next
    INDEX
    Explanations

    the word "multi-" followed by a variety of different terms or contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to "multi-" prefixed terms indicating various multi-faceted concepts

    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
     Bauer
    -0.77
    姫
    -0.76
    士
    -0.75
    Ö¼
    -0.74
     Wonderland
    -0.73
    furt
    -0.73
     Malik
    -0.71
     Ludwig
    -0.67
     Grind
    -0.67
     Prophet
    -0.67
    POSITIVE LOGITS
    icult
    0.95
    cro
    0.91
    ilingual
    0.87
    locking
    0.86
    absor
    0.83
     multic
    0.81
    ples
    0.80
    multi
    0.78
     multit
    0.78
    acet
    0.76
    Activations Density 0.009%

    No Known Activations