© 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. 10-RES-JB
    11. 5438
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "from time to time

    oai_token-act-pair · gpt-3.5-turbo

    references to time and temporal expressions

    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
    rored
    -0.78
    acerb
    -0.65
    reon
    -0.58
    ogie
    -0.58
     DRAGON
    -0.56
     Lank
    -0.56
    iol
    -0.56
     Trop
    -0.55
    cipl
    -0.54
    YS
    -0.53
    POSITIVE LOGITS
     standpoint
    0.95
     outset
    0.90
     inception
    0.86
     vantage
    0.73
     onwards
    0.72
     perspective
    0.70
    ratch
    0.70
     till
    0.69
     onward
    0.69
     bearer
    0.68
    Activations Density 0.040%

    No Known Activations