© 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. 11-RES-JB
    11. 14875
    Prev
    Next
    INDEX
    Explanations

    timestamps in a specific format, specifically with a focus on the minute and second values

    oai_token-act-pair · gpt-3.5-turbo

    date and time formats

    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
     endors
    -0.75
    channelAvailability
    -0.68
    lessly
    -0.66
     kinderg
    -0.64
    isSpecialOrderable
    -0.64
     prolifer
    -0.61
    comes
    -0.60
    ationally
    -0.59
     fearful
    -0.58
     pil
    -0.56
    POSITIVE LOGITS
     GMT
    1.22
     CET
    1.10
     IST
    1.08
     UTC
    1.05
    GMT
    1.02
     PDT
    0.97
    UTC
    0.92
     EDT
    0.90
    :{
    0.85
     PST
    0.85
    Activations Density 0.032%

    No Known Activations