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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 13538
    Prev
    Next
    INDEX
    Explanations

    time-related phrases or events

    oai_token-act-pair · gpt-3.5-turbo

    the word "since" and its variations to indicate the passage of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abus
    -0.63
    abor
    -0.61
    igraph
    -0.61
    addons
    -0.61
    inders
    -0.58
    ãĥĻ
    -0.57
    avis
    -0.56
    itect
    -0.56
    opsis
    -0.55
     %%
    -0.55
    POSITIVE LOGITS
     then
    1.40
    rely
    1.06
    then
    0.97
     THEN
    0.94
     Then
    0.88
     retiring
    0.87
    Then
    0.85
     arriving
    0.79
     inception
    0.75
     2009
    0.74
    Activations Density 0.044%

    No Known Activations