© 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. 11-RES-JB
    11. 9515
    Prev
    Next
    INDEX
    Explanations

    phrases relating to discussions or reports on various topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases or expressions indicating inquiry or curiosity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rouse
    -0.64
    dozen
    -0.64
     ÂŃ
    -0.62
    ixty
    -0.61
    ensable
    -0.61
    oples
    -0.60
    isans
    -0.59
    ighty
    -0.59
    olit
    -0.58
    omical
    -0.58
    POSITIVE LOGITS
     OnePlus
    0.90
     Cyan
    0.87
     systemd
    0.85
     Xiaomi
    0.85
     Ubuntu
    0.85
     Ryzen
    0.84
     AMD
    0.83
     Nvidia
    0.83
     DirectX
    0.82
     Valve
    0.82
    Activations Density 0.691%

    No Known Activations