INDEX

Explanations

phrases indicating opinion, preference, and correctness in reasoning

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

proportions or likelihood

np_acts-logits-general · gemini-2.0-flash

majority / most

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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



-0.59

 nakalista

-0.54

Autoritní

-0.47

 RouterModule

-0.46

uxxxx

-0.42

exitRule

-0.39

AxisAlignment

-0.37

sizeCache

-0.36

🇶

-0.36

的一种

-0.36

POSITIVE LOGITS

 meisten

2.22

 most

2.19

 majority

2.16

 maioria

2.11

 plupart

2.08

 большинство

2.08

 большин

2.08

 meeste

2.08

大多数

2.02

 kebanyakan

2.02

Activations Density 0.877%

phrases indicating opinion, preference, and correctness in reasoning

proportions or likelihood

majority / most

No Comments

No Known Activations