INDEX

Explanations

negations and references to the absence of something

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

no

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

fast

-0.39

most

-0.38

Tu

-0.36

ss

-0.35

 fast

-0.35

so

-0.34

 damit

-0.34

Dec

-0.33

are

-0.33

Ai

-0.33

POSITIVE LOGITS



0.72

IsContent

0.64

OGND

0.63

舺

0.63

 تضيفلها

0.62

GEBURTS

0.60

 transfieras

0.59

новниш

0.58

featureID

0.57

 мәкал

0.57

Activations Density 0.138%

negations and references to the absence of something

no

No Comments

No Known Activations