INDEX

Explanations

phrases indicating support or advocacy for political positions or actions

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

"for" followed by various words

np_acts-logits-general · gemini-2.0-flash

for the

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

verwijspagina

-0.55

<!--[

-0.51

Figure

-0.49

-0.48

 cuales

-0.48

 ngữ

-0.47

されており

-0.47

-0.46

 indeed

-0.45

POSITIVE LOGITS

 them

0.79

.*")]

0.76

]")]

0.71

Rüyada

0.70

and

0.70

 &___

0.68

GOTREF

0.67

 springfox

0.67

 ***!

0.66

ReusableCell

0.64

Activations Density 0.427%

phrases indicating support or advocacy for political positions or actions

"for" followed by various words

for the

No Comments

No Known Activations