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. 8-RES-JB
    6. 23369
    Prev
    Next
    INDEX
    Explanations

    comparative and superlative statements related to quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    comparative or quantitative phrases indicating differences or increases in measurements

    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
    Mand
    -0.77
    redd
    -0.73
    alg
    -0.70
    uly
    -0.70
    wcsstore
    -0.66
    egu
    -0.64
    dump
    -0.63
    gyn
    -0.63
    blogs
    -0.62
    other
    -0.61
    POSITIVE LOGITS
     than
    1.13
     Than
    0.96
    than
    0.85
    ngth
    0.81
     per
    0.80
     ($
    0.72
     gross
    0.71
     (£
    0.70
    illion
    0.69
     apiece
    0.69
    Activations Density 0.124%

    No Known Activations