© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 17025
    Prev
    Next
    INDEX
    Explanations

    phrases related to time and daylight saving

    oai_token-act-pair · gpt-3.5-turbo

    terms related to daylight and its variations

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

    No Comments

    Negative Logits
    essee
    -0.81
    ilage
    -0.81
    Dur
    -0.80
    CVE
    -0.80
    Bey
    -0.78
    */(
    -0.77
    cho
    -0.76
    ttle
    -0.75
    ressor
    -0.73
    Arch
    -0.70
    POSITIVE LOGITS
     Daylight
    1.14
     daylight
    1.13
     Saving
    0.99
    etheless
    0.87
    urnal
    0.77
     Hour
    0.74
     daytime
    0.71
     CST
    0.71
     Sahara
    0.70
     saving
    0.70
    Activations Density 0.006%

    No Known Activations