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. 21187
    Prev
    Next
    INDEX
    Explanations

    past tense verb phrases with 'have' followed by another verb

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey hypothetical scenarios or past experiences involving the phrase "would not 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
     UL
    -0.66
    iaz
    -0.62
     moratorium
    -0.61
     FI
    -0.61
     disclaimer
    -0.61
     fundament
    -0.59
     Clause
    -0.59
     quarry
    -0.59
     Everywhere
    -0.57
     PIN
    -0.57
    POSITIVE LOGITS
     anymore
    0.99
     bothered
    0.95
     necessarily
    0.81
     mattered
    0.80
    icable
    0.79
     cared
    0.78
    yet
    0.75
    icably
    0.74
    hin
    0.74
    zos
    0.72
    Activations Density 0.143%

    No Known Activations