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. 0-RES-JB
    6. 19571
    Prev
    Next
    INDEX
    Explanations

    phrases related to human rights

    oai_token-act-pair · gpt-3.5-turbo

    references to human rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     charger
    -0.71
    itz
    -0.69
    oard
    -0.68
    styles
    -0.67
    bub
    -0.66
     upstairs
    -0.66
     condos
    -0.66
    charg
    -0.66
     tariff
    -0.66
     rentals
    -0.66
    POSITIVE LOGITS
     Human
    3.69
    Human
    3.01
     human
    2.24
    human
    2.14
     Humans
    2.01
     HUM
    1.65
    humans
    1.61
     Humanity
    1.61
     Mankind
    1.55
     humans
    1.49
    Activations Density 0.015%

    No Known Activations