INDEX

Explanations

terms related to adverse reactions and side effects of medications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 للمعارف

-0.62

脚注の使い方

-0.61

 tartalomajánló

-0.60

ativistic

-0.49

 Hamm

-0.47

 Strategic

-0.45

 strategic

-0.45

 Fairview

-0.45

 ISNI

-0.45

ריק

-0.45

POSITIVE LOGITS

 symptoms

0.87

effects

0.85

 effects

0.85

 Effects

0.81

Symptoms

0.76

 effets

0.75

symptoms

0.74

 Symptoms

0.73

Effects

0.71

 symptom

0.71

Activations Density 0.637%

terms related to adverse reactions and side effects of medications

No Comments

No Known Activations