© 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. 20872
    Prev
    Next
    INDEX
    Explanations

    time-related phrases, particularly those mentioning durations or lengths

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "how long" in various contexts

    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
    Reviewed
    -0.74
    istine
    -0.71
    ruck
    -0.67
    leck
    -0.64
    itational
    -0.64
    ulkan
    -0.63
    udic
    -0.63
    atche
    -0.63
    VR
    -0.62
    anooga
    -0.62
    POSITIVE LOGITS
    itud
    0.94
     ago
    0.94
     enough
    0.86
     awaited
    0.83
     overdue
    0.83
    long
    0.82
    entimes
    0.81
     longer
    0.79
    sword
    0.78
     stretches
    0.75
    Activations Density 0.046%

    No Known Activations