© 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. 0-RES-JB
    11. 16402
    Prev
    Next
    INDEX
    Explanations

    phrases related to the introduction of something

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pots
    -0.83
    ply
    -0.79
    conserv
    -0.71
    pot
    -0.69
     knots
    -0.68
    vest
    -0.67
    tmp
    -0.66
    licts
    -0.63
     owed
    -0.63
    eters
    -0.62
    POSITIVE LOGITS
     introduction
    3.80
     introdu
    2.54
     Introduction
    2.16
    introdu
    2.13
     introducing
    1.91
     introduce
    1.88
     reintrodu
    1.81
     introductory
    1.66
    Introduction
    1.65
     Introdu
    1.62
    Activations Density 0.009%

    No Known Activations