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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-RES-JB
    6. 16657
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or processes that are developing or happening

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "unfold" and its variations, indicating a focus on the gradual development or progression of events

    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
    anyon
    -0.71
    ogun
    -0.69
    uana
    -0.68
    alty
    -0.67
    aving
    -0.67
    avering
    -0.67
    pping
    -0.67
    este
    -0.67
    king
    -0.66
    osponsors
    -0.65
    POSITIVE LOGITS
     unfold
    1.32
     unfolded
    1.25
     unfolding
    1.18
     unfolds
    1.16
    ĸļ
    1.13
     Afric
    0.83
     tremend
    0.79
    entimes
    0.79
     unravel
    0.75
    daq
    0.74
    Activations Density 0.012%

    No Known Activations