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. 21783
    Prev
    Next
    INDEX
    Explanations

    comparative statements involving the term 'more'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "more" indicating a comparative increase or abundance

    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
    xtap
    -0.79
    atan
    -0.70
    Ħ
    -0.66
    ovie
    -0.65
     Newly
    -0.63
    ĺħ
    -0.63
    rompt
    -0.63
    §
    -0.62
    ģ
    -0.62
    ode
    -0.62
    POSITIVE LOGITS
     than
    1.41
     Than
    1.04
     mileage
    0.98
     stringent
    0.98
     ado
    0.96
    than
    0.90
     flexibility
    0.87
    natureconservancy
    0.86
     bang
    0.85
     importantly
    0.84
    Activations Density 0.142%

    No Known Activations