© 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. 10-RES-JB
    11. 8113
    Prev
    Next
    INDEX
    Explanations

    time-related phrases and deadlines

    oai_token-act-pair · gpt-3.5-turbo

    mentions of time durations and deadlines

    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
     parach
    -0.63
     Fountain
    -0.62
    Redd
    -0.61
     torches
    -0.60
    Tro
    -0.59
    اÙĦ
    -0.59
     Punk
    -0.58
    acus
    -0.58
    bent
    -0.58
     sor
    -0.58
    POSITIVE LOGITS
     duration
    1.11
     depending
    1.11
     elapsed
    1.08
    depending
    1.06
     intervals
    1.02
     gestation
    0.95
     apiece
    0.93
     respectively
    0.92
     ago
    0.92
     thereafter
    0.91
    Activations Density 0.115%

    No Known Activations