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. 1741
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the state of Oklahoma

    oai_token-act-pair · gpt-3.5-turbo

    references to the state of Oklahoma

    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
    BOOK
    -0.79
    âĸ¬âĸ¬
    -0.77
     istg
    -0.75
    advertisement
    -0.73
    ########
    -0.71
    fare
    -0.71
    TING
    -0.68
    ching
    -0.68
     Uriel
    -0.68
    âĸ¬
    -0.68
    POSITIVE LOGITS
    lahoma
    1.07
     City
    0.99
     Instruments
    0.90
    essee
    0.90
     Springs
    0.84
     Rapids
    0.82
     Haram
    0.81
     Soon
    0.81
    oms
    0.79
    oya
    0.76
    Activations Density 0.010%

    No Known Activations