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. 0-RES-JB
    6. 14407
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of inevitability

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating certainty or inevitability

    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
    len
    -0.68
    apon
    -0.66
    wan
    -0.66
     Percent
    -0.65
    ibur
    -0.63
    let
    -0.62
    gem
    -0.60
     Tun
    -0.60
     Wing
    -0.59
    emen
    -0.59
    POSITIVE LOGITS
     inevitable
    3.56
     unavoidable
    2.43
     inev
    2.03
     inevitably
    1.62
     imminent
    1.54
     unthinkable
    1.47
     impending
    1.46
     unstoppable
    1.44
     obligatory
    1.37
     unforeseen
    1.37
    Activations Density 0.018%

    No Known Activations