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. 2045
    Prev
    Next
    INDEX
    Explanations

    the specific time reference "week" within text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "this week" or references to recent events in a temporal context

    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
    gery
    -0.72
    itialized
    -0.63
    ggle
    -0.63
    erate
    -0.61
    UES
    -0.60
    vae
    -0.59
    vec
    -0.59
     perpetual
    -0.59
     ut
    -0.59
    Control
    -0.58
    POSITIVE LOGITS
     afternoon
    0.81
     evening
    0.75
     marked
    0.73
    flower
    0.72
     subpoen
    0.72
     unveiling
    0.71
     announcing
    0.71
     ç¥ŀ
    0.70
    lished
    0.68
    女
    0.67
    Activations Density 0.107%

    No Known Activations