© 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. 20642
    Prev
    Next
    INDEX
    Explanations

    time-related phrases such as lengths of time and hours worked

    oai_token-act-pair · gpt-3.5-turbo

    references to units of time and age

    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
    ifice
    -0.74
    icably
    -0.72
    INST
    -0.66
    culus
    -0.65
    untled
    -0.64
    emis
    -0.64
    ashtra
    -0.63
    thy
    -0.63
    ingu
    -0.63
    hin
    -0.63
    POSITIVE LOGITS
     olds
    1.27
     increments
    1.23
     intervals
    1.11
    frames
    1.01
     equivalents
    0.90
     periods
    0.90
     cycles
    0.85
     lengths
    0.85
    rees
    0.82
     spans
    0.81
    Activations Density 0.082%

    No Known Activations