© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 2723
    Prev
    Next
    INDEX
    Explanations

    time-related words and phrases such as 'dawn', 'midnight', 'dusk', and 'daylight'

    oai_token-act-pair · gpt-3.5-turbo

    time-related terms, especially those referring to specific times of day

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lde
    -0.77
    stan
    -0.76
    İĭ
    -0.73
    arte
    -0.72
    Bey
    -0.72
    itsch
    -0.70
    oice
    -0.68
    ques
    -0.68
    pha
    -0.67
    ophy
    -0.66
    POSITIVE LOGITS
     hours
    1.00
     curfew
    1.00
     EDT
    0.99
     PDT
    0.95
     prayers
    0.93
    fall
    0.93
     commute
    0.91
     ET
    0.89
     EST
    0.88
     sunrise
    0.87
    Activations Density 0.064%

    No Known Activations