© 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. 7894
    Prev
    Next
    INDEX
    Explanations

    phrases related to opting out or unsubscribing

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the concept of time flexibility or the ability to take action at any moment

    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
    ãĤ©
    -0.76
    ties
    -0.73
    inav
    -0.68
    geries
    -0.66
    rats
    -0.64
    flush
    -0.63
    ges
    -0.63
    iates
    -0.63
    icut
    -0.62
    ér
    -0.62
    POSITIVE LOGITS
     time
    1.18
    time
    0.99
     moment
    0.87
    TIME
    0.85
     Time
    0.83
     TIME
    0.78
     point
    0.75
    Time
    0.73
    Station
    0.73
     given
    0.71
    Activations Density 0.022%

    No Known Activations