INDEX

Explanations

references to knowledge and understanding in various contexts

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

"knowledge"

np_acts-logits-general · gemini-2.0-flash

knowledge of

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AndEndTag

-0.67

SBATCH

-0.66

SizeF

-0.65

válasz

-0.61

ofollow

-0.59

jelent

-0.58

StructEnd

-0.57

UserDao

-0.57

 relâche

-0.56

dymyr

-0.55

POSITIVE LOGITS

 knowledge

1.21

 Knowledge

1.17

Knowledge

1.15

knowledge

1.13

 KNOWLEDGE

0.93

 connaissances

0.83

 base

0.82

base

0.81

 knowled

0.81

 Wissens

0.79

Activations Density 0.056%

references to knowledge and understanding in various contexts

"knowledge"

knowledge of

No Comments

No Known Activations