INDEX

Explanations

subjective conjectures or possibilities regarding events or situations

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

preceding commas like "perhaps" and "maybe."

np_acts-logits-general · gemini-2.0-flash

perhaps, maybe, possibly

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

ğunu

-0.50

可靠

-0.46

 apparently

-0.45

ANGA

-0.43

setRight

-0.42

 highly

-0.42

 consistently

-0.42

anga

-0.41

บาท

-0.41

 transform

-0.41

POSITIVE LOGITS

 BorderSide

0.84

HasAnnotation

0.78

migrationBuilder

0.77

WireFormatLite

0.75

enumi

0.74

 oprot

0.74

InSection

0.72

protoimpl

0.70

URLException

0.70

 insuffisamment

0.70

Activations Density 0.232%

subjective conjectures or possibilities regarding events or situations

preceding commas like "perhaps" and "maybe."

perhaps, maybe, possibly

No Comments

No Known Activations