INDEX

Explanations

terms related to injuries and accidents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

<bos>

-0.65

 Normdatei

-0.41

viewDidLoad

-0.41

",@"

-0.41

iség

-0.41

')['

-0.40

 khúc

-0.40

 excell

-0.39

 Entomol

-0.39

NewLabel

-0.38

POSITIVE LOGITS

 injuries

0.84

 unlucky

0.80

 utafitiHapana

0.79

 injury

0.79

 onCancelled

0.77

 Injuries

0.77

parsedMessage

0.76

تقاوى

0.76

WebVitals

0.75

 accidents

0.73

Activations Density 0.347%

terms related to injuries and accidents

No Comments

No Known Activations