© 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. 20596
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditions or limitations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the existence or state of subjects and actions in various contexts

    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
    inav
    -0.75
     Zot
    -0.64
     Lack
    -0.61
     havoc
    -0.59
    icles
    -0.58
    VIDIA
    -0.56
    icol
    -0.56
    âĿ
    -0.55
     srfAttach
    -0.55
    natureconservancy
    -0.55
    POSITIVE LOGITS
     to
    1.26
     supposed
    1.24
    to
    1.14
     obliged
    0.98
    To
    0.94
     thereto
    0.92
     destined
    0.91
     gonna
    0.91
     obligated
    0.90
     TO
    0.90
    Activations Density 0.284%

    No Known Activations