INDEX

Explanations

references to fire and burning in various contexts

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

fire

np_acts-logits-general · gemini-2.0-flash

fire and burning

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

XtraGrid

-0.58

 '\\;'

-0.57

AddHtmlAttribute

-0.57

forRoot

-0.53

енча

-0.49

 ویکی‌پدی

-0.49

 pembe

-0.47

stateProvider

-0.47

GetKeyDown

-0.47

nitzel

-0.45

POSITIVE LOGITS

 fire

2.48

 fires

2.23

 burning

2.13

 flames

2.11

 Fire

2.06

Fire

2.04

fire

2.03

 FIRE

1.97

FIRE

1.91

 flame

1.90

Activations Density 0.320%

references to fire and burning in various contexts

fire

fire and burning

No Comments

No Known Activations