© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 7010
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the passage of time since a specific event or action occurred

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the passage of time or duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĹĺ
    -0.82
    asio
    -0.58
    edience
    -0.57
    ingu
    -0.57
    aires
    -0.57
    aneously
    -0.57
    lect
    -0.57
    acion
    -0.56
    Weapon
    -0.56
    first
    -0.56
    POSITIVE LOGITS
     awhile
    1.34
     raining
    0.97
     decades
    0.88
     speculated
    0.88
     months
    0.86
     years
    0.86
     downhill
    0.85
     ages
    0.84
     rumored
    0.82
     YEAR
    0.82
    Activations Density 0.055%

    No Known Activations