INDEX

Explanations

terms related to pharmacology or drugs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 متعلقه

-0.72

-0.68

 مرئيه

-0.64

ときに

-0.63

kyou

-0.62

dì

-0.61

eta

-0.60

Gambas

-0.60

evich

-0.60

Activité

-0.60

POSITIVE LOGITS

er

1.01

ER

0.75

rrr

0.68

rrrrr

0.68

rrrr

0.67

rrrrrr

0.62

rrrrrrrr

0.62

RRRR

0.55

 sembler

0.53

0.52

Activations Density 0.357%

terms related to pharmacology or drugs

No Comments

No Known Activations