© 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. 17566
    Prev
    Next
    INDEX
    Explanations

    dates represented as numerical multiples of years

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to age or duration in years

    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
     Mek
    -0.81
     proport
    -0.79
     vulner
    -0.78
     Pok
    -0.74
     sacrific
    -0.73
     elim
    -0.72
     Phi
    -0.71
     Rez
    -0.70
     mic
    -0.70
     skelet
    -0.69
    POSITIVE LOGITS
    old
    1.90
    olds
    1.58
    long
    1.49
    period
    1.44
    older
    1.42
    span
    1.28
    plus
    1.25
    history
    1.25
    Old
    1.24
    OLD
    1.21
    Activations Density 0.034%

    No Known Activations