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. 3291
    Prev
    Next
    INDEX
    Explanations

    terms related to promoting or increasing awareness on various topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to raising awareness on various social issues

    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
    ãĥĥãĥī
    -0.72
    hetti
    -0.71
    compan
    -0.67
    rett
    -0.66
    Textures
    -0.63
    coni
    -0.63
    scenes
    -0.61
    anova
    -0.61
     rou
    -0.60
     Arkham
    -0.59
    POSITIVE LOGITS
     awareness
    1.22
    awareness
    1.00
     Awareness
    0.98
    ibility
    0.80
    fulness
    0.78
    irtual
    0.76
    ledged
    0.74
    ?????
    0.73
    orship
    0.72
    uggest
    0.72
    Activations Density 0.024%

    No Known Activations