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. 7-RES-JB
    6. 21995
    Prev
    Next
    INDEX
    Explanations

    mentions of missed opportunities or regrets

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "could have" and its variations, often in a context suggesting missed opportunities or potential actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Mem
    -0.59
     Kis
    -0.57
     Clear
    -0.55
    of
    -0.55
    bert
    -0.55
     adamant
    -0.54
     craving
    -0.53
     Corpus
    -0.53
    ocol
    -0.53
     corps
    -0.53
    POSITIVE LOGITS
     been
    1.02
     gotten
    1.00
    ħĭ
    0.90
    ivably
    0.89
    idon
    0.84
    been
    0.84
     avoided
    0.83
     gone
    0.78
     Been
    0.77
     taken
    0.73
    Activations Density 0.033%

    No Known Activations