© 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. 0-RES-JB
    11. 2787
    Prev
    Next
    INDEX
    Explanations

    terms related to something coming to light or becoming known

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "emerge" and its variations, indicating a focus on the concept of new developments or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Section
    -0.61
     count
    -0.55
     Pun
    -0.55
    rating
    -0.55
    Dou
    -0.54
     wrong
    -0.54
    XL
    -0.54
     Customer
    -0.53
    ki
    -0.53
     GO
    -0.53
    POSITIVE LOGITS
     emerged
    3.51
     emerges
    2.70
     emerge
    2.43
     surfaced
    2.06
     arose
    1.90
     arisen
    1.67
     sprang
    1.66
     erupted
    1.54
     transpired
    1.53
     appeared
    1.52
    Activations Density 0.011%

    No Known Activations