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. 23202
    Prev
    Next
    INDEX
    Explanations

    phrases related to equality and fairness

    oai_token-act-pair · gpt-3.5-turbo

    references to equality and equal rights

    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
    HI
    -0.83
    ARCH
    -0.82
    UX
    -0.79
    berries
    -0.76
    stal
    -0.74
    OLOG
    -0.73
    ARP
    -0.70
    Assembly
    -0.70
     PubMed
    -0.69
    stra
    -0.69
    POSITIVE LOGITS
    itably
    0.95
    izers
    0.92
    itarian
    0.90
    itable
    0.84
    izer
    0.83
    itability
    0.79
    izes
    0.78
    equal
    0.78
    etrical
    0.78
    equality
    0.76
    Activations Density 0.014%

    No Known Activations