© 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. 12153
    Prev
    Next
    INDEX
    Explanations

    phrases related to time, such as "days," "weeks," "months," and "hours."

    oai_token-act-pair · gpt-3.5-turbo

    references to the passage of time, specifically days and weeks

    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
    Reviewer
    -0.81
    acus
    -0.79
     Encyclopedia
    -0.64
    adium
    -0.64
    inite
    -0.62
    illions
    -0.61
    antine
    -0.60
    kefeller
    -0.58
    alg
    -0.58
    alien
    -0.58
    POSITIVE LOGITS
     ago
    1.65
     Ago
    1.16
     beforehand
    1.00
     shy
    0.96
     before
    0.96
     earlier
    0.93
     later
    0.93
     prior
    0.93
     ahead
    0.87
    pring
    0.85
    Activations Density 0.073%

    No Known Activations