Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9096
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a comparison or contrast between different entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    the word "while" and its variations suggesting contrast or simultaneous actions

    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
    iotic
    -0.88
    Register
    -0.86
    ahime
    -0.85
    illet
    -0.83
    hack
    -0.81
    wow
    -0.81
    kr
    -0.80
    matter
    -0.79
    orb
    -0.79
    isphere
    -0.79
    POSITIVE LOGITS
     others
    1.21
     retaining
    1.12
     simultaneously
    1.11
     maintaining
    1.10
     awaiting
    0.94
     preserving
    0.94
     acknowledging
    0.92
     ignoring
    0.91
     insisting
    0.88
     ensuring
    0.86
    Activations Density 0.045%

    No Known Activations