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. 19921
    Prev
    Next
    INDEX
    Explanations

    phrases related to social and economic policies and interventions

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to fairness and community support in 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
     exclaim
    -0.71
     exclaimed
    -0.68
     summed
    -0.64
    tumblr
    -0.62
     summarizes
    -0.62
     anecd
    -0.60
    cember
    -0.58
     summarized
    -0.57
     laughed
    -0.55
     describes
    -0.54
    POSITIVE LOGITS
     viable
    0.67
     profitable
    0.66
     sustainable
    0.64
     profitability
    0.63
     footing
    0.63
     financially
    0.63
     faire
    0.60
     meaningful
    0.58
     future
    0.58
     lucrative
    0.58
    Activations Density 1.254%

    No Known Activations