INDEX

Explanations

statements regarding the concept of "fact."

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

"fact that"

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 @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Erben

-0.66

fú

-0.65

ContentAsync

-0.63

ագրություններ

-0.62

Discografia

-0.60

DY

-0.60

endpush

-0.59

importe

-0.58

isbury

-0.57

ICAGO

-0.57

POSITIVE LOGITS

 fact

1.56

 FACT

1.43

 Fact

1.31

fact

1.28

FACT

1.26

Fact

1.15

 facts

1.01

 Facts

0.96

 Tatsache

0.96

facts

0.91

Activations Density 0.081%

statements regarding the concept of "fact."

"fact that"

the fact that

No Comments

No Known Activations