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. 20641
    Prev
    Next
    INDEX
    Explanations

    victims of various situations or issues

    oai_token-act-pair · gpt-3.5-turbo

    references to victims of various crimes and injustices

    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
    oday
    -0.82
    MX
    -0.76
    yip
    -0.74
    soDeliveryDate
    -0.74
    ulum
    -0.74
    readable
    -0.70
    ortment
    -0.69
    ary
    -0.69
    heit
    -0.68
    rier
    -0.68
    POSITIVE LOGITS
     ingest
    0.80
     gou
    0.71
     metic
    0.69
     psych
    0.68
     suff
    0.66
     untreated
    0.66
     displacement
    0.64
     starvation
    0.63
    Ö¼
    0.63
     either
    0.63
    Activations Density 0.083%

    No Known Activations