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. 21211
    Prev
    Next
    INDEX
    Explanations

    verbs indicating action or change in a specific context

    oai_token-act-pair · gpt-3.5-turbo

    verbs associated with actions and concepts in social, political, and economic contexts

    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
    ĺħ
    -0.69
     Hurricanes
    -0.64
    utenberg
    -0.62
     Dolphins
    -0.61
    IZE
    -0.61
    allery
    -0.61
     foremost
    -0.59
     constitu
    -0.59
     Legislative
    -0.59
     Directorate
    -0.58
    POSITIVE LOGITS
    ings
    1.56
    able
    1.47
    ables
    1.43
    ability
    1.21
    ers
    1.20
    ational
    1.08
    aways
    1.07
    away
    1.05
    backs
    1.05
    ement
    1.02
    Activations Density 0.516%

    No Known Activations