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. 0-RES-JB
    6. 21701
    Prev
    Next
    INDEX
    Explanations

    technological advancements or updates mentioned in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that begin with the word "Now."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     moder
    -0.72
     repr
    -0.65
     lax
    -0.62
     abusive
    -0.59
     severe
    -0.59
     improvised
    -0.58
     gru
    -0.57
     moderate
    -0.57
     fatal
    -0.57
     reflex
    -0.56
    POSITIVE LOGITS
    Now
    3.22
     Now
    2.45
    now
    2.05
    NOW
    1.89
    Today
    1.69
    Then
    1.69
     NOW
    1.65
    Next
    1.54
    Since
    1.53
    So
    1.52
    Activations Density 0.014%

    No Known Activations