INDEX

Explanations

mentions of the coronavirus pandemic and related medical terms

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

transQ

-0.63

enumi

-0.59

PyTuple

-0.50

 пре

-0.43

 client

-0.41

</

-0.41

Client

-0.40

↵↵

-0.39

nag

-0.39

POSITIVE LOGITS

Coronavirus

0.98

 Coronavirus

0.92

coronavirus

0.92

 coronavirus

0.92

 Wuhan

0.85

 COVID

0.80

onavir

0.80

قایناق‌لار

0.78

Corona

0.78

 Corona

0.77

Activations Density 0.347%

mentions of the coronavirus pandemic and related medical terms

No Comments

No Known Activations