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

    Neuronpedia

    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. 6700
    Prev
    Next
    INDEX
    Explanations

    specific times of day or events

    oai_token-act-pair · gpt-3.5-turbo

    time-related information, specifically for scheduled broadcasts or events

    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
    cig
    -0.93
    rob
    -0.87
    sch
    -0.87
    bole
    -0.84
     tremend
    -0.84
    sole
    -0.83
    saf
    -0.83
    shr
    -0.83
    bre
    -0.83
    organ
    -0.82
    POSITIVE LOGITS
     PM
    1.80
     AM
    1.67
     GMT
    1.47
     BST
    1.36
     EDT
    1.36
     UTC
    1.33
     PST
    1.31
     EST
    1.31
     PDT
    1.30
     PT
    1.29
    Activations Density 0.059%

    No Known Activations