INDEX

Explanations

terms related to occupational safety and health regulations

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IsUnicode

-0.40

 frumos

-0.32

 gorgeous

-0.32

 Weltkrieg

-0.31

 xinh

-0.31

 very

-0.30

Dam

-0.30

 aprobación

-0.30

曖昧さ回避

-0.29

 cantik

-0.29

POSITIVE LOGITS

 OSHA

0.74

OSHA

0.74

 faſt

0.64

 Houſe

0.59

 pleaſure

0.58

Workplace

0.57

 EconPapers

0.56

Occupational

0.56

 ſind

0.56

 ſei

0.55

Activations Density 0.010%

terms related to occupational safety and health regulations

No Comments

No Known Activations