© 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. 1-RES-JB
    11. 14466
    Prev
    Next
    INDEX
    Explanations

    phrases related to official statements or decisions

    oai_token-act-pair · gpt-3.5-turbo

    the word "regarding" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orah
    -0.75
     Sabha
    -0.72
     Notting
    -0.71
    ahi
    -0.67
    eri
    -0.66
    aden
    -0.64
    ©¶æ¥µ
    -0.63
    hearted
    -0.63
    ammy
    -0.63
    chard
    -0.62
    POSITIVE LOGITS
     regarding
    0.88
     Regarding
    0.83
     respecting
    0.72
    eous
    0.71
    ä¿
    0.70
     concerning
    0.70
    utical
    0.69
     pertaining
    0.69
    iversal
    0.64
     coerc
    0.64
    Activations Density 0.010%

    No Known Activations