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. 10-RES-JB
    6. 37
    Prev
    Next
    INDEX
    Explanations

    descriptions related to life events and experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to personal life experiences or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aye
    -0.92
     Cosponsors
    -0.79
    armed
    -0.68
     ratios
    -0.67
     EW
    -0.66
     Deadline
    -0.65
     attribution
    -0.65
    Rat
    -0.64
     Elk
    -0.64
    arms
    -0.64
    POSITIVE LOGITS
     shortened
    0.83
     glamorous
    0.82
     revolves
    0.82
     intertwined
    0.81
     ruined
    0.81
     adventures
    0.81
     whirlwind
    0.80
     adventure
    0.80
     forfeit
    0.79
     fortunes
    0.79
    Activations Density 0.201%

    No Known Activations