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. 7640
    Prev
    Next
    INDEX
    Explanations

    names of individuals, potentially famous or influential

    oai_token-act-pair · gpt-3.5-turbo

    names or surnames of individuals

    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
    udeb
    -0.70
    soDeliveryDate
    -0.67
    FactoryReloaded
    -0.66
     governors
    -0.63
     modifiers
    -0.63
     demoral
    -0.63
    Plex
    -0.62
     shorth
    -0.61
     legitimacy
    -0.61
    ADRA
    -0.61
    POSITIVE LOGITS
     Jr
    1.32
     Sr
    0.99
     III
    0.95
     (@
    0.92
    nen
    0.88
    chuk
    0.86
    owski
    0.86
    sson
    0.85
     writes
    0.84
    zyk
    0.83
    Activations Density 0.287%

    No Known Activations