INDEX

Explanations

phrases related to adverse drug reactions and safety information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Manifesto

-0.45

tô

-0.44

mologie

-0.43

 Tener

-0.43

Ends

-0.42

شهاد

-0.42

 stand

-0.41

Red

-0.40

moveToFirst

-0.39

 helpless

-0.39

POSITIVE LOGITS

AndEndTag

0.81

 mergeFrom

0.78

kloped

0.73

 risk

0.73

 adverse

0.73

 समीक्षाओं

0.70

RegressionTest

0.68

VersionUID

0.68

choenen

0.66

ArrowToggle

0.65

Activations Density 0.637%

phrases related to adverse drug reactions and safety information

No Comments

No Known Activations