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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5483
    Prev
    Next
    INDEX
    Explanations

    the phrase "a couple of" followed by a number or a relative time frame

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "a couple of" frequently used in various contexts

    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
    acus
    -0.78
    urden
    -0.77
     agre
    -0.74
    gow
    -0.70
    omnia
    -0.69
    CHO
    -0.68
    ļéĨĴ
    -0.68
    =]
    -0.67
    omorph
    -0.66
    hes
    -0.66
    POSITIVE LOGITS
     dozen
    1.29
     hundred
    1.13
    dozen
    0.92
    teenth
    0.90
     thousand
    0.88
     paragraphs
    0.84
     tablespoons
    0.83
     clicks
    0.80
    teen
    0.80
     weeks
    0.80
    Activations Density 0.057%

    No Known Activations