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. 4147
    Prev
    Next
    INDEX
    Explanations

    phrases related to government committees or panels

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the phrase 'on' followed by a number or topic

    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
    SourceFile
    -0.76
     bins
    -0.67
     smugglers
    -0.66
    DragonMagazine
    -0.66
     trough
    -0.66
    gallery
    -0.66
    DERR
    -0.65
    bleacher
    -0.65
     traffickers
    -0.64
     scoop
    -0.64
    POSITIVE LOGITS
     behalf
    1.12
     Aging
    0.88
    eday
    0.87
    ision
    0.75
     Accountability
    0.74
    etheless
    0.74
     Capitol
    0.74
     Medium
    0.73
    etime
    0.72
     Motion
    0.71
    Activations Density 0.061%

    No Known Activations