© 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. 2908
    Prev
    Next
    INDEX
    Explanations

    statements or remarks made by people

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate statements or remarks made by individuals

    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
    ventures
    -0.82
    inav
    -0.80
     Benefits
    -0.79
    population
    -0.76
    letal
    -0.74
     strugg
    -0.74
     Flavoring
    -0.73
    iencies
    -0.72
    axis
    -0.71
    ulnerability
    -0.70
    POSITIVE LOGITS
     uttered
    1.26
     echoed
    1.22
     prophetic
    1.17
     laced
    1.17
     sarcastic
    1.17
     insulting
    1.15
     scathing
    1.14
     inflammatory
    1.13
     provocative
    1.12
     retweet
    1.12
    Activations Density 0.270%

    No Known Activations