INDEX

Explanations

phrases related to monitoring or keeping track of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

UpInside

-0.71

IGraphics

-0.57

abestanden

-0.56

AtIndexPath

-0.54

ngths

-0.54

PMailer

-0.54

λικά

-0.52

UrlResolution

-0.52

ParallelGroup

-0.52

 يتيمه

-0.51

POSITIVE LOGITS

 watch

1.91

 monitoring

1.88

 monitor

1.75

 Watch

1.69

 keep

1.68

 Monitoring

1.67

watch

1.64

 watching

1.64

Monitoring

1.61

 monitored

1.58

Activations Density 0.270%

phrases related to monitoring or keeping track of something

No Comments

No Known Activations