Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 16945
    Prev
    Next
    INDEX
    Explanations

    words related to the gradual development or progression of events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "unfold" and its variations, indicating developments or events in progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uana
    -0.78
    iked
    -0.77
    alty
    -0.76
    ondo
    -0.72
    unte
    -0.72
    ogun
    -0.71
    este
    -0.69
    chens
    -0.69
    exc
    -0.68
    ogo
    -0.64
    POSITIVE LOGITS
     unfold
    1.31
     unfolding
    1.21
     unfolded
    1.15
     unfolds
    1.08
    ĸļ
    0.85
     Afric
    0.82
    URES
    0.81
     anew
    0.79
     Tanz
    0.75
     unravel
    0.72
    Activations Density 0.028%

    No Known Activations