© 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. 18704
    Prev
    Next
    INDEX
    Explanations

    phrases related to occurrences or events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "happen" and its variants, indicating events or situations that take place

    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
     Flavoring
    -0.64
     Flags
    -0.63
    ij士
    -0.58
    ilts
    -0.56
    ä½ľ
    -0.56
    orters
    -0.55
    ãĥ³ãĤ¸
    -0.55
     adequ
    -0.54
    KC
    -0.54
    oves
    -0.53
    POSITIVE LOGITS
     spontaneously
    1.04
     naturally
    0.88
     catast
    0.84
     happen
    0.80
    uate
    0.80
     unexpectedly
    0.79
    cffffcc
    0.79
     anywhere
    0.78
     randomly
    0.77
     unpredict
    0.77
    Activations Density 0.074%

    No Known Activations