INDEX

Explanations

phrases related to long-term duration or processes

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

"Long"

np_acts-logits-general · gemini-2.0-flash

long duration or extent

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tonode

-0.91

Datuak

-0.84

 Monfieur

-0.80

 bezeichneter

-0.75

 myſelf

-0.74

})));

-0.74

queryInterface

-0.72

$.

-0.71

();)

-0.70

 AssemblyTitle

-0.70

POSITIVE LOGITS

 LONG

0.95

 long

0.94

 Long

0.90

long

0.89

Long

0.86

ago

0.86

 term

0.82

 Longo

0.78

LONG

0.77

 lasting

0.73

Activations Density 0.160%

phrases related to long-term duration or processes

"Long"

long duration or extent

No Comments

No Known Activations