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. 16570
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings or representations

    oai_token-act-pair · gpt-3.5-turbo

    references to legal cases and legal representation

    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
    nesday
    -0.66
     Vaugh
    -0.61
     referen
    -0.56
    enegger
    -0.51
    '."
    -0.51
     incent
    -0.49
     disadvant
    -0.49
    vertisement
    -0.49
    maxwell
    -0.49
    retty
    -0.48
    POSITIVE LOGITS
    )]
    0.54
     )]
    0.50
    pires
    0.49
    )?
    0.42
    ÂŃ
    0.38
     Tatt
    0.38
    othing
    0.38
    )—
    0.38
    photos
    0.37
    )|
    0.37
    Activations Density 2.468%

    No Known Activations