INDEX

Explanations

phrases that indicate examples, references, or justifications in a text

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

"general"

np_acts-logits-general · gemini-2.0-flash

general trends principles

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

出版年

-0.84

rungsseite

-0.82

 للمعارف

-0.77

 kasarigan

-0.75

mappedBy

-0.69

 nakalista

-0.62

 通販

-0.60

SourceChecksum

-0.60

 AssemblyProduct

-0.59

 AssemblyTitle

-0.59

POSITIVE LOGITS

 general

2.20

 basic

1.97

general

1.81

basic

1.68

 generally

1.67

大致

1.53

 generales

1.49

generally

1.48

基本

1.47

Basic

1.45

Activations Density 0.887%

phrases that indicate examples, references, or justifications in a text

"general"

general trends principles

No Comments

No Known Activations