© 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. 16356
    Prev
    Next
    INDEX
    Explanations

    instances where the word "had" is used with an emphasis or importance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "had."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     auto
    -0.67
     automatic
    -0.63
     cookie
    -0.63
     envelope
    -0.63
     appearance
    -0.62
     shape
    -0.62
     imp
    -0.60
     outward
    -0.60
     ens
    -0.59
     enc
    -0.59
    POSITIVE LOGITS
    had
    4.24
    has
    1.83
    Had
    1.78
    was
    1.62
    didn
    1.56
    were
    1.51
    did
    1.39
    ha
    1.35
    hid
    1.34
     Had
    1.34
    Activations Density 0.013%

    No Known Activations