INDEX

Explanations

references to "flat" in various contexts, including objects, surfaces, and conditions

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

"flat" or its variations

np_acts-logits-general · gemini-2.0-flash

flat followed by various words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

tagHelperRunner

-0.81

TargetException

-0.75

OGND

-0.71

queryInterface

-0.71

NOPQRST

-0.67

onAttach

-0.66

 Италијани

-0.66

]")]

-0.65

 متعلقه

-0.63

FormTagHelper

-0.63

POSITIVE LOGITS

 flat

1.05

 Flat

1.04

Flat

0.96

flat

0.94

 FLAT

0.94

FLAT

0.93

 flats

0.81

 Flats

0.80

tened

0.79

flats

0.72

Activations Density 0.071%

references to "flat" in various contexts, including objects, surfaces, and conditions

"flat" or its variations

flat followed by various words

No Comments

No Known Activations