INDEX

Explanations

terms related to injuries 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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ddot

-0.77

Sok

-0.70

setAll

-0.69

Sok

-0.67

Sop

-0.67

ব

-0.64

>−

-0.63

esseract

-0.63

unched

-0.61

sop

-0.60

POSITIVE LOGITS

 injury

2.13

 injuries

2.09

 Injury

2.05

 Injuries

1.99

Injury

1.95

injury

1.85

Injuries

1.78

 injured

1.77

INJ

1.72

 Injured

1.62

Activations Density 0.087%

terms related to injuries and medical conditions

No Comments

No Known Activations