© 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. 4-RES-JB
    11. 7503
    Prev
    Next
    INDEX
    Explanations

    references to driverless technology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "less" or "reduced" in various contexts

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

    No Comments

    Negative Logits
     Younger
    -0.81
     ç¥ŀ
    -0.78
    女
    -0.77
     Whitman
    -0.72
     Cain
    -0.71
     Osiris
    -0.71
     Pilgrim
    -0.71
     Maiden
    -0.71
     Magicka
    -0.70
     Clan
    -0.70
    POSITIVE LOGITS
    undai
    0.90
     policing
    0.89
     inference
    0.86
     therap
    0.84
     practition
    0.83
    aviour
    0.82
     pursuits
    0.81
     diagn
    0.78
     livest
    0.78
    VIDIA
    0.78
    Activations Density 0.052%

    No Known Activations