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. 3118
    Prev
    Next
    INDEX
    Explanations

    references to ongoing issues or events

    oai_token-act-pair · gpt-3.5-turbo

    references to ongoing events or issues

    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
    ingers
    -0.92
    yp
    -0.79
    ique
    -0.78
    oak
    -0.77
    pper
    -0.76
    ppers
    -0.76
    acked
    -0.75
    imble
    -0.75
    otle
    -0.74
    fing
    -0.74
    POSITIVE LOGITS
     developments
    1.01
     ongoing
    1.00
     hostilities
    0.90
     upkeep
    0.86
     investigations
    0.84
     saga
    0.84
     unresolved
    0.84
     tense
    0.82
     efforts
    0.81
     discussions
    0.77
    Activations Density 0.017%

    No Known Activations