© 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. 12947
    Prev
    Next
    INDEX
    Explanations

    references to time durations

    oai_token-act-pair · gpt-3.5-turbo

    references to the length or time of events or processes

    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
    riad
    -0.91
    ramid
    -0.83
    illard
    -0.77
    bold
    -0.73
    artisan
    -0.72
    iasis
    -0.71
    tical
    -0.70
    inis
    -0.69
    habi
    -0.68
    rim
    -0.67
    POSITIVE LOGITS
     duration
    1.14
    duration
    0.97
    Duration
    0.92
     destro
    0.82
     interval
    0.78
     length
    0.78
     periods
    0.78
     dur
    0.78
     lasting
    0.77
     elapsed
    0.76
    Activations Density 0.012%

    No Known Activations