© 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. 8-RES-JB
    11. 4085
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a passage of time or progression of events

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference the concept of time passage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BILITY
    -0.62
    osphere
    -0.61
     Nirvana
    -0.58
    spot
    -0.58
    ä
    -0.57
     understatement
    -0.57
    ittal
    -0.57
     supra
    -0.56
     Phantom
    -0.55
    BLE
    -0.54
    POSITIVE LOGITS
    whelming
    1.15
    whel
    1.10
    lap
    1.05
    heard
    1.01
    come
    0.99
    flow
    0.98
    lying
    0.98
    haul
    0.97
    dose
    0.97
    ride
    0.95
    Activations Density 0.033%

    No Known Activations