© 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. 8-RES-JB
    11. 9456
    Prev
    Next
    INDEX
    Explanations

    hyphenated numbers

    oai_token-act-pair · gpt-3.5-turbo

    phrases and references related to numerical values and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rica
    -0.79
     Proc
    -0.76
     Minerva
    -0.72
     Prometheus
    -0.71
     Illum
    -0.69
     Compass
    -0.67
     Duo
    -0.66
     Cassidy
    -0.65
     Ins
    -0.64
     Scully
    -0.63
    POSITIVE LOGITS
    year
    1.34
    month
    1.30
    months
    1.23
    figure
    1.20
    member
    1.19
    Ele
    1.17
    hour
    1.15
    pack
    1.15
    years
    1.14
    minute
    1.14
    Activations Density 0.077%

    No Known Activations