© 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. 22672
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "ai" (artificial intelligence)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Kai" and its variations, indicating a focus on that particular individual

    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
    things
    -0.62
    staking
    -0.59
    idges
    -0.59
    mort
    -0.58
    milo
    -0.58
    ALLY
    -0.58
     lucky
    -0.58
     traction
    -0.57
     MEM
    -0.57
    odder
    -0.57
    POSITIVE LOGITS
    ya
    1.18
    ju
    1.16
    jin
    1.14
    yah
    1.09
    yan
    1.08
    wan
    1.06
    jan
    1.04
    ji
    1.02
    yang
    0.97
    wa
    0.96
    Activations Density 0.063%

    No Known Activations