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. 8-RES-JB
    6. 5404
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and medical contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to enrollment or commitment in programs or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -0.75
     erupted
    -0.72
     headlined
    -0.66
    iframe
    -0.65
     alluded
    -0.65
    etta
    -0.64
    itta
    -0.64
     anecd
    -0.64
    issues
    -0.63
     tweets
    -0.62
    POSITIVE LOGITS
     whichever
    0.87
     boarding
    0.76
     predetermined
    0.76
     Psychiatric
    0.75
     segregated
    0.75
    irtual
    0.74
     resettlement
    0.73
     reputable
    0.73
     unregulated
    0.72
    ospital
    0.72
    Activations Density 0.507%

    No Known Activations