INDEX

Explanations

phrases related to negation and obstacles in discussions or arguments

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

that mean "to hinder" or "prevent"

np_acts-logits-general · gemini-2.0-flash

hindering or preventing progress

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

igshid

-0.55

 لينك

-0.51

piecze

-0.50

 résidence

-0.49

менте

-0.48

pisah

-0.47

GenerationType

-0.47

telegram

-0.47

 Maintenant

-0.46

 viciss

-0.46

POSITIVE LOGITS

 progress

0.73

好不容易

0.71

せっかく

0.66

InjectAttribute

0.66

 effectiveness

0.63

 otherwise

0.58

正常的

0.57

SharedDtor

0.56

 OTHERWISE

0.56

 valuable

0.55

Activations Density 0.500%

phrases related to negation and obstacles in discussions or arguments

that mean "to hinder" or "prevent"

hindering or preventing progress

No Comments

No Known Activations