© 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. 9-RES-JB
    11. 13844
    Prev
    Next
    INDEX
    Explanations

    numbers that represent statistics or data points

    oai_token-act-pair · gpt-3.5-turbo

    sentences that contain numerical data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     parach
    -0.72
     pudding
    -0.66
     trouble
    -0.66
     philos
    -0.66
     tentative
    -0.63
     recycling
    -0.63
     elusive
    -0.62
     snowball
    -0.61
     distilled
    -0.61
     sourcing
    -0.61
    POSITIVE LOGITS
    95
    1.30
    5
    1.27
    97
    1.25
    00
    1.24
    9
    1.23
    7
    1.23
    98
    1.23
    94
    1.19
    04
    1.19
    06
    1.19
    Activations Density 0.078%

    No Known Activations