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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 23923
    Prev
    Next
    INDEX
    Explanations

    specific references to object identifiers or object-related terms in a programming context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Object" and related concepts in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     millenn
    -0.93
    DAY
    -0.92
    mph
    -0.83
    creen
    -0.81
    Film
    -0.80
    ornia
    -0.77
    icago
    -0.76
    aturdays
    -0.74
    HAEL
    -0.74
    inventoryQuantity
    -0.73
    POSITIVE LOGITS
     Object
    0.84
    ives
    0.80
     objects
    0.80
    dump
    0.80
     obj
    0.78
     Token
    0.74
    ively
    0.74
     Obj
    0.74
     object
    0.73
    object
    0.73
    Activations Density 0.011%

    No Known Activations