Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 9633
    Prev
    Next
    INDEX
    Explanations

    mentions of human rights organizations and policies

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations or concepts related to human rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Copyright
    -0.59
     Flavoring
    -0.56
    inas
    -0.54
    taboola
    -0.54
    iership
    -0.53
    DCS
    -0.52
    UFC
    -0.51
    Scroll
    -0.51
    Published
    -0.51
    south
    -0.50
    POSITIVE LOGITS
     moreover
    0.89
     however
    0.89
     therefore
    0.88
     furthermore
    0.81
     meanwhile
    0.79
     also
    0.70
    anwhile
    0.69
     additionally
    0.66
     thus
    0.66
     though
    0.60
    Activations Density 2.742%

    No Known Activations