© 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. 2-RES-JB
    11. 10423
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific person or location, potentially related to news or events

    oai_token-act-pair · gpt-3.5-turbo

    specific names or references, particularly related to people or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ¦
    -0.90
     GEAR
    -0.69
     Yel
    -0.69
     exha
    -0.69
     TABLE
    -0.69
    ces
    -0.67
     antidepressants
    -0.65
     IGF
    -0.65
     resil
    -0.65
     unanim
    -0.65
    POSITIVE LOGITS
    cht
    1.01
    mann
    0.95
    ronics
    0.95
    fried
    0.88
    itect
    0.86
    ung
    0.86
    geist
    0.84
    iness
    0.83
    idy
    0.82
    ijn
    0.80
    Activations Density 0.004%

    No Known Activations