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. 801
    Prev
    Next
    INDEX
    Explanations

    words related to a sense of inevitability or certainty

    oai_token-act-pair · gpt-3.5-turbo

    expressions of inevitability or certainty about outcomes or events

    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
     Arbor
    -0.59
     Lem
    -0.58
    ework
    -0.57
    classified
    -0.56
    Pay
    -0.55
     Hold
    -0.54
    izer
    -0.54
    ______
    -0.52
     Licensed
    -0.52
     Plan
    -0.51
    POSITIVE LOGITS
     inevitably
    3.45
     invariably
    2.52
     unavoid
    2.06
     predictably
    1.62
     undoubtedly
    1.50
     surely
    1.41
     understandably
    1.36
     doubtless
    1.34
     naturally
    1.31
     unsurprisingly
    1.25
    Activations Density 0.013%

    No Known Activations