INDEX

Explanations

medical terms or conditions

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

Appears after numbers/integers

np_acts-logits-general · gemini-2.0-flash

selective apoptosis caspase

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

########.

-0.93

 EconPapers

-0.87

 Signalez

-0.80

expandindo

-0.80

AccessorTable

-0.78

MigrationBuilder

-0.78

sizeCache

-0.77

 المعيارى

-0.74

contentLoaded

-0.73

出版年

-0.73

POSITIVE LOGITS

↵↵

0.58

</tr>

0.54

 ejus

0.50

 eorum

0.49

 pisang

0.48

 necessárias

0.43

menea

0.42

 pudesse

0.41

éről

0.41

“……”

0.40

Activations Density 0.119%

medical terms or conditions

Appears after numbers/integers

selective apoptosis caspase

No Comments

No Known Activations