© 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. 3759
    Prev
    Next
    INDEX
    Explanations

    mentions of bottled items

    oai_token-act-pair · gpt-3.5-turbo

    references to bottled water and specific individuals associated with it

    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
    daq
    -1.08
    nesota
    -1.01
    hare
    -0.88
    atten
    -0.85
    cloth
    -0.84
    crop
    -0.84
    abeth
    -0.83
    asus
    -0.80
    atos
    -0.79
    eth
    -0.78
    POSITIVE LOGITS
    awei
    0.82
     bottled
    0.80
    é¾
    0.74
     RG
    0.73
     Hib
    0.70
     BALL
    0.69
    BALL
    0.69
    æ©Ł
    0.68
     Memories
    0.67
    ãĥŁ
    0.66
    Activations Density 0.025%

    No Known Activations