© 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. 7-RES-JB
    11. 13381
    Prev
    Next
    INDEX
    Explanations

    references to time related to specific events that happened years ago

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the passage of time, particularly those mentioning years or months

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lict
    -0.71
    inite
    -0.69
    ocate
    -0.67
    roth
    -0.66
    licts
    -0.65
    ahime
    -0.63
    ropy
    -0.63
    olis
    -0.62
    plet
    -0.60
    omorphic
    -0.60
    POSITIVE LOGITS
     ago
    1.53
     Ago
    1.11
    long
    0.90
     overdue
    0.87
     later
    0.76
    é¾įå¥ij士
    0.75
     apart
    0.74
     ahead
    0.74
     Later
    0.73
     earlier
    0.73
    Activations Density 0.087%

    No Known Activations