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. 10-RES-JB
    6. 21300
    Prev
    Next
    INDEX
    Explanations

    phrases related to making sense or not making sense

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing the concept of making sense or lack thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     manually
    -0.81
     diligently
    -0.66
     privately
    -0.64
     cautioned
    -0.62
    Guest
    -0.61
    alus
    -0.59
     laced
    -0.59
     reserved
    -0.59
     carefully
    -0.59
     extensively
    -0.58
    POSITIVE LOGITS
     difference
    1.43
     sense
    1.35
    sense
    1.19
     Difference
    1.17
     Sense
    1.05
     mockery
    1.02
     dent
    0.98
     impression
    0.90
    ENSE
    0.89
     headlines
    0.85
    Activations Density 0.086%

    No Known Activations