© 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. 2-RES-JB
    11. 922
    Prev
    Next
    INDEX
    Explanations

    modifiers indicating an extended duration or length, such as "long-time" and "long-distance"

    oai_token-act-pair · gpt-4-turbo

    phrases related to the concept of passage of time or duration, oftentimes in the context of personal experiences or interactions

    oai_token-act-pair · gpt-3.5-turbo

    references to duration and distance in time and space

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.97
    lez
    -0.68
    ById
    -0.67
     GEAR
    -0.65
    =-=-=-=-
    -0.64
    <?
    -0.64
     relegation
    -0.64
    psons
    -0.63
    Spons
    -0.62
     Moy
    -0.61
    POSITIVE LOGITS
    kered
    0.74
    ogene
    0.71
    edly
    0.66
    rency
    0.65
    otine
    0.64
    nered
    0.64
    theless
    0.64
    ago
    0.63
    iatus
    0.63
    sighted
    0.61
    Activations Density 0.410%

    No Known Activations