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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 7957
    Prev
    Next
    INDEX
    Explanations

    names and positions of politicians and officials

    oai_token-act-pair · gpt-3.5-turbo

    references to Getty Images or other visual media credits related to political events

    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
     Cobb
    -0.66
     toler
    -0.63
     sed
    -0.63
     carpet
    -0.62
     esteemed
    -0.62
     racially
    -0.62
    apolis
    -0.61
     favor
    -0.60
     scattered
    -0.60
     endeavour
    -0.60
    POSITIVE LOGITS
    EVA
    0.81
    Closure
    0.80
    AFP
    0.78
    pmwiki
    0.77
    events
    0.77
    photo
    0.76
    Film
    0.75
    Getty
    0.74
    camera
    0.74
    Art
    0.72
    Activations Density 0.031%

    No Known Activations