INDEX

Explanations

terms related to "flatness" in various contexts

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

"flat"

np_acts-logits-general · gemini-2.0-flash

words starting with flat

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

 Réalisation

-0.59

TargetException

-0.57

 متعلقه

-0.57

нциклопедия

-0.54

OGND

-0.52

@+

-0.51

onAttach

-0.49

 antecedentes

-0.49

StructEnd

-0.47

 précie

-0.47

POSITIVE LOGITS

 flat

1.00

tened

0.97

 Flat

0.97

 FLAT

0.89

Flat

0.89

flat

0.87

ulence

0.81

FLAT

0.81

tens

0.75

tener

0.73

Activations Density 0.132%

terms related to "flatness" in various contexts

"flat"

words starting with flat

No Comments

No Known Activations