© 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. 6601
    Prev
    Next
    INDEX
    Explanations

    instances of the word "will" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "will" indicating future actions 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
     dating
    -0.64
    gging
    -0.60
     obsessed
    -0.60
     Columbus
    -0.58
     packed
    -0.58
     sync
    -0.57
     crowded
    -0.57
     cracking
    -0.57
     compartment
    -0.57
     similar
    -0.56
    POSITIVE LOGITS
    will
    3.97
    shall
    1.79
    would
    1.75
    Will
    1.71
    might
    1.53
     WILL
    1.50
    won
    1.48
    must
    1.44
    could
    1.43
    should
    1.42
    Activations Density 0.013%

    No Known Activations