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. 5-RES-JB
    6. 863
    Prev
    Next
    INDEX
    Explanations

    dates in the mid-20th century, particularly the years 1949, 1950, 1951, 1953, and events related to those years

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years, particularly around the mid-20th century

    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
    hed
    -0.84
    tro
    -0.83
    resso
    -0.80
    hes
    -0.75
    ithe
    -0.72
    atories
    -0.67
    inventoryQuantity
    -0.64
    EStreamFrame
    -0.64
    act
    -0.62
    hesis
    -0.62
    POSITIVE LOGITS
    å¹
    0.71
     Eisenhower
    0.71
     1946
    0.70
    -'
    0.64
     1958
    0.63
     1947
    0.63
    chev
    0.62
    çļ
    0.62
     1952
    0.62
     1949
    0.61
    Activations Density 0.021%

    No Known Activations