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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 7-RES-JB
    6. 6557
    Prev
    Next
    INDEX
    Explanations

    expressions related to periods of time such as "every year" or "each year"

    oai_token-act-pair · gpt-3.5-turbo

    references to annual events or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ociate
    -0.81
    tymology
    -0.77
    MpServer
    -0.72
    bent
    -0.71
    aleb
    -0.68
    agra
    -0.67
    ymm
    -0.66
    jri
    -0.66
    artisan
    -0.66
    emort
    -0.65
    POSITIVE LOGITS
     thereafter
    1.05
     throughout
    0.83
    lins
    0.83
    night
    0.79
     until
    0.77
     Iw
    0.70
     except
    0.68
    until
    0.66
     basis
    0.65
     whenever
    0.63
    Activations Density 0.077%

    No Known Activations