© 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. 6692
    Prev
    Next
    INDEX
    Explanations

    specific times of days and days of the week

    oai_token-act-pair · gpt-3.5-turbo

    specific time indicators and numerical values related to scheduling

    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
    isations
    -0.81
    currency
    -0.76
    notations
    -0.70
    errors
    -0.68
    BBC
    -0.68
    versions
    -0.67
    IGN
    -0.66
    intern
    -0.65
    safe
    -0.65
    edIn
    -0.64
    POSITIVE LOGITS
     p
    1.23
     pm
    0.97
     noon
    0.88
    ½
    0.83
     pa
    0.80
     o
    0.79
     hr
    0.78
     pt
    0.78
     Ãł
    0.77
     min
    0.76
    Activations Density 0.044%

    No Known Activations