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. 6-RES-JB
    6. 11406
    Prev
    Next
    INDEX
    Explanations

    phrases expressing regret or missed opportunities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express regret or hindsight involving the verb "have"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hostage
    -0.74
     maze
    -0.68
    opian
    -0.61
     muse
    -0.60
     craving
    -0.60
    ori
    -0.60
    Trivia
    -0.58
     Gins
    -0.58
     Wid
    -0.57
    Mem
    -0.56
    POSITIVE LOGITS
     gotten
    0.99
     been
    0.93
    gotten
    0.91
    been
    0.83
     done
    0.78
     behaved
    0.76
     avoided
    0.76
     taken
    0.75
    ¶ħ
    0.74
     existed
    0.74
    Activations Density 0.036%

    No Known Activations