© 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. 10-RES-JB
    11. 10114
    Prev
    Next
    INDEX
    Explanations

    time-related phrases or durations

    oai_token-act-pair · gpt-3.5-turbo

    phrases referring to future time frames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     1956
    -0.76
     Chosen
    -0.74
     1958
    -0.73
     1959
    -0.73
     Inher
    -0.70
     1986
    -0.70
     reinvent
    -0.70
    1989
    -0.69
     1989
    -0.69
     1955
    -0.69
    POSITIVE LOGITS
     afternoon
    1.21
     week
    1.19
     hours
    1.12
    Tuesday
    1.12
    Monday
    1.11
    Wednesday
    1.11
     morning
    1.10
     hour
    1.09
     Wednesday
    1.09
     Monday
    1.08
    Activations Density 0.295%

    No Known Activations