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. 23276
    Prev
    Next
    INDEX
    Explanations

    the phrase "hard to" followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express difficulty or challenge in performing an action or task

    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
    leys
    -0.65
    bats
    -0.65
    afety
    -0.65
    LES
    -0.64
    written
    -0.64
    mails
    -0.62
    ARA
    -0.61
    agents
    -0.61
    cand
    -0.60
    lings
    -0.60
    POSITIVE LOGITS
     imagine
    1.23
     reconcile
    1.13
     convince
    1.09
     conceive
    1.07
     distinguish
    1.06
     quantify
    1.05
     achieve
    1.02
     discern
    1.00
     compare
    1.00
     understand
    1.00
    Activations Density 0.058%

    No Known Activations