INDEX

Explanations

terms indicating slight variations in characteristics or qualities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

kal

-0.75

læ

-0.66

jangkau

-0.66

дол

-0.65

 Schaefer

-0.62

`${

-0.62

……

-0.61

,[

-0.60

kon

-0.59

 Winnie

-0.59

POSITIVE LOGITS

slightly

2.08

 slightly

2.08

 Slightly

1.95

Slightly

1.88

Slight

1.67

 slight

1.66

 légèrement

1.60

 ligeramente

1.56

 Slight

1.54

 leggermente

1.52

Activations Density 0.103%

terms indicating slight variations in characteristics or qualities

No Comments

No Known Activations