INDEX

Explanations

terms related to fire and firefighting situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 tartalomajánló

-1.02

theless

-0.96

 betweenstory

-0.96

ItemBackground

-0.95

 Roskov

-0.94

 EconPapers

-0.93

WebVitals

-0.92

]").

-0.92

 Мексичка

-0.91

 Jacobsen

-0.89

POSITIVE LOGITS

 FIRE

1.47

Fire

1.47

 Fire

1.44

fire

1.43

 fire

1.40

FIRE

1.39

 fires

1.32

 Fires

1.16

火

1.13

fires

1.11

Activations Density 0.031%

terms related to fire and firefighting situations

No Comments

No Known Activations