INDEX

Explanations

phrases that express precision or specificity in terms of description or details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ModelForm

-0.71

Ser

-0.70

Ser

-0.69

 laminate

-0.63

aio

-0.62

ご了承

-0.61

PMailer

-0.60

 layui

-0.60

 invokingState

-0.60

 Giles

-0.59

POSITIVE LOGITS

 exactly

2.29

exactly

2.20

 Exactly

2.18

Exactly

2.03

 EXACTLY

1.86

 exact

1.83

 exactement

1.72

 Exact

1.69

 precisely

1.67

 exac

1.63

Activations Density 0.062%

phrases that express precision or specificity in terms of description or details

No Comments

No Known Activations