© 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. 5727
    Prev
    Next
    INDEX
    Explanations

    numbers followed by a percentage

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly those presented in percentages

    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
    Helper
    -0.75
    Hub
    -0.72
    aucus
    -0.70
    Broad
    -0.70
    behind
    -0.69
    guide
    -0.69
    Offline
    -0.68
    LAN
    -0.67
    helps
    -0.67
    hesion
    -0.67
    POSITIVE LOGITS
     thousand
    1.26
     percent
    1.08
     hundred
    1.06
     cents
    1.02
    teen
    0.92
    eenth
    0.91
     dollars
    0.91
     eighty
    0.89
     forty
    0.86
    percent
    0.86
    Activations Density 0.046%

    No Known Activations