© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16566
    Prev
    Next
    INDEX
    Explanations

    medical conditions or terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate ongoing states or conditions

    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
     Furious
    -0.74
     Awakens
    -0.73
    still
    -0.66
    Profile
    -0.64
    now
    -0.63
    âĺħ
    -0.63
    arta
    -0.62
     Contents
    -0.59
    ottage
    -0.58
    Dialogue
    -0.57
    POSITIVE LOGITS
     likened
    1.13
     criticized
    1.05
     criticised
    0.99
     dubbed
    0.97
     extensively
    0.95
     proven
    0.94
     debated
    0.93
     interpreted
    0.92
     shown
    0.92
     steadily
    0.92
    Activations Density 0.115%

    No Known Activations