© 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. 10031
    Prev
    Next
    INDEX
    Explanations

    names of historical figures and philosophical concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to influential figures and their associated theories or concepts in historical and political 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
    ebin
    -0.76
    netflix
    -0.72
     srfAttach
    -0.72
     Tickets
    -0.70
    Exit
    -0.70
     Streaming
    -0.69
     Reporter
    -0.68
    aspx
    -0.66
     clips
    -0.66
     Parenthood
    -0.66
    POSITIVE LOGITS
     believed
    1.25
     envisioned
    1.23
     formulated
    1.23
     advocated
    1.20
     wrote
    1.18
     coined
    1.17
     understood
    1.16
     preached
    1.15
     invented
    1.14
     mathemat
    1.14
    Activations Density 0.276%

    No Known Activations