Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 3420
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming objects, such as "Object", and specific programming-related terms like "serializer", "executable", and "metadata"

    oai_token-act-pair · gpt-3.5-turbo

    references to object-oriented programming concepts and structures

    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
    DAY
    -0.93
    creen
    -0.89
     millenn
    -0.85
    mph
    -0.79
    ornia
    -0.78
    Film
    -0.77
    WAYS
    -0.77
    coni
    -0.74
     Deity
    -0.71
    kers
    -0.71
    POSITIVE LOGITS
    dump
    0.80
    imately
    0.78
    ifications
    0.78
     obj
    0.77
     Object
    0.76
     objects
    0.74
    handled
    0.74
    ives
    0.74
    object
    0.73
    ively
    0.72
    Activations Density 0.013%

    No Known Activations