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. 409
    Prev
    Next
    INDEX
    Explanations

    information related to data gathering and processing, especially in the context of community intelligence or business operations

    oai_token-act-pair · gpt-3.5-turbo

    references to collected or sourced information

    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
    wagen
    -0.87
    Interstitial
    -0.72
    quit
    -0.71
    interstitial
    -0.70
    Fail
    -0.67
    Push
    -0.64
    ogun
    -0.62
     toler
    -0.62
    Ô
    -0.62
     succeed
    -0.61
    POSITIVE LOGITS
    enhagen
    0.96
     glean
    0.87
     Steele
    0.79
    çīĪ
    0.74
     Oracle
    0.73
     dossier
    0.71
    transfer
    0.71
     gathered
    0.71
    phia
    0.69
    processing
    0.69
    Activations Density 0.453%

    No Known Activations