INDEX

Explanations

references to specific groups or entities associated with "Hunter" or "Pacific."

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

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

ン

-0.92

й

-0.90

__*/

-0.81

一个

-0.78

ReusableCell

-0.76

 UnityEditor

-0.74

keiten

-0.73

ers

-0.71

к

-0.69

/−

-0.67

POSITIVE LOGITS

ians

1.03

ology

0.98

ième

0.93

ised

0.86

oto

0.85

0.84

ological

0.79

しまう

0.77

۰

0.77

ologically

0.75

Activations Density 0.859%

references to specific groups or entities associated with "Hunter" or "Pacific."

No Comments

No Known Activations