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. 4-RES-JB
    6. 23722
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of neutrality or being unbiased

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to neutrality and impartiality

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

    No Comments

    Negative Logits
    Hop
    -0.86
    soDeliveryDate
    -0.84
    Mill
    -0.82
    MA
    -0.77
    RESULTS
    -0.76
    HAEL
    -0.76
    MAT
    -0.74
    Amazing
    -0.74
    FAQ
    -0.74
    ENG
    -0.73
    POSITIVE LOGITS
    izing
    1.05
    izes
    1.03
    izers
    1.00
    utral
    0.99
    ization
    0.97
     neutral
    0.94
    izer
    0.92
    ize
    0.89
    ized
    0.89
     neutrality
    0.88
    Activations Density 0.014%

    No Known Activations