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. 9-RES-JB
    6. 16843
    Prev
    Next
    INDEX
    Explanations

    phrases related to events that happen annually or periodically

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "year" or "time period" consistently

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arton
    -0.80
    ociate
    -0.71
    ouf
    -0.69
    bent
    -0.63
    yz
    -0.63
    ophon
    -0.63
    eny
    -0.62
    acebook
    -0.62
    bley
    -0.62
    uron
    -0.61
    POSITIVE LOGITS
     thereafter
    1.14
     throughout
    0.76
     since
    0.72
     until
    0.71
    til
    0.66
    night
    0.66
    long
    0.66
     anniversary
    0.63
    lins
    0.63
     except
    0.63
    Activations Density 0.067%

    No Known Activations