INDEX

Explanations

terms related to health risks and medical conditions

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

+#+#

-0.76

Jîn

-0.72

 للاسماء

-0.68

ContentAsync

-0.68

 становника

-0.67

adpleegd

-0.67

 الحره

-0.64

хьтан

-0.64

 transfieras

-0.62

nloa

-0.60

POSITIVE LOGITS

 caused

2.43

due

2.39

due

2.04

caused

2.02

 Caused

1.85

 akibat

1.84

DUE

1.78

Due

1.75

 causado

1.73

Due

1.71

Activations Density 1.750%

terms related to health risks and medical conditions

No Comments

No Known Activations