INDEX

Explanations

opinions and subjective assessments of experiences or topics

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

Tokens that begin a contrasting phrase

np_acts-logits-general · gemini-2.0-flash

greatest / biggest / most

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

 snippetHide

-0.56

 endwhile

-0.54

IContainer

-0.52

soever

-0.47

#!/

-0.45

ValueStyle

-0.44

 onResponse

-0.42

 springfox

-0.42

BeanUtils

-0.41

 exact

-0.41

POSITIVE LOGITS

 greatest

0.91

 biggest

0.89

greatest

0.85

何より

0.82

biggest

0.82

 najbardziej

0.82

 najwięks

0.79

 proudest

0.79

Biggest

0.79

重点

0.77

Activations Density 0.298%

opinions and subjective assessments of experiences or topics

Tokens that begin a contrasting phrase

greatest / biggest / most

No Comments

No Known Activations