© 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. 10481
    Prev
    Next
    INDEX
    Explanations

    dates expressed as a number (e.g., "26")

    oai_token-act-pair · gpt-3.5-turbo

    numerical values indicating time or durations

    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
    apon
    -0.62
     âĸº
    -0.62
     Tradable
    -0.62
    interstitial
    -0.61
    Pri
    -0.61
    notation
    -0.60
    NUM
    -0.60
     âĢ
    -0.60
    zu
    -0.59
    quote
    -0.59
    POSITIVE LOGITS
     years
    1.66
     months
    1.53
     weeks
    1.38
     seasons
    1.35
    years
    1.34
     decades
    1.34
    months
    1.31
     consecutive
    1.24
     generations
    1.24
     days
    1.24
    Activations Density 0.120%

    No Known Activations