INDEX

Explanations

phrases that highlight contrasting or contradictory information

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

Followed by the word "fact"

np_acts-logits-general · gemini-2.0-flash

the fact that

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

OGND

-0.61

 للمعارف

-0.61

 تانيه

-0.60

mybatisplus

-0.58

RegistryLite

-0.58

TypedDataSet

-0.58

{/

-0.57

Архівовано

-0.57

TestingModule

-0.56

InputBorder

-0.55

POSITIVE LOGITS

 fact

2.62

 Tatsache

1.86

fact

1.86

 feit

1.61

 faptul

1.57

 fato

1.43

 hecho

1.36

 fatto

1.35

Fact

1.32

 Fact

1.32

Activations Density 0.647%

phrases that highlight contrasting or contradictory information

Followed by the word "fact"

the fact that

No Comments

No Known Activations