© 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. 11-RES-JB
    11. 10084
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or anticipation for future outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating anticipation of future events or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exting
    -0.62
     cumbers
    -0.58
    earchers
    -0.56
    nor
    -0.56
     inaccessible
    -0.55
     metic
    -0.54
     pseudonym
    -0.54
    stro
    -0.54
    IDS
    -0.54
     captcha
    -0.54
    POSITIVE LOGITS
     how
    1.09
     what
    0.91
     whether
    0.84
     soon
    0.84
     whats
    0.82
     why
    0.80
     shortly
    0.78
     alot
    0.78
     him
    0.78
     tomorrow
    0.77
    Activations Density 0.104%

    No Known Activations