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. 8-RES-JB
    6. 20003
    Prev
    Next
    INDEX
    Explanations

    comparisons of quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating quantities that exceed a certain amount

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĺħ
    -0.85
    xtap
    -0.82
    DragonMagazine
    -0.70
    UCK
    -0.62
    imaru
    -0.61
    OCK
    -0.58
     ILCS
    -0.58
    IPS
    -0.58
    Guard
    -0.58
    imer
    -0.58
    POSITIVE LOGITS
     than
    1.47
    than
    1.11
     Than
    0.98
     importantly
    0.93
     ado
    0.86
     stringent
    0.85
     elaborate
    0.78
    worldly
    0.77
     sophisticated
    0.75
     nuanced
    0.74
    Activations Density 0.141%

    No Known Activations