© 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. 10336
    Prev
    Next
    INDEX
    Explanations

    words related to legal issues and specific places

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases with the suffix "et."

    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
    ¥ŀ
    -0.75
    ĸļ
    -0.72
     obser
    -0.71
    FTWARE
    -0.69
     undermin
    -0.67
    ĻĤ
    -0.64
     Sco
    -0.64
     Conquer
    -0.64
    Downloadha
    -0.63
     Witcher
    -0.63
    POSITIVE LOGITS
    roit
    1.13
    ernal
    1.04
    ilde
    1.00
    ilon
    0.98
    rics
    0.98
    rix
    0.97
    ted
    0.97
    zel
    0.96
    rov
    0.96
    iquette
    0.95
    Activations Density 0.021%

    No Known Activations