INDEX

Explanations

references to rates and their values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 onCreateView

-0.75

 Montserrat

-0.67

Архівовано

-0.67

."+

-0.64

 Parsons

-0.63

illères

-0.61

¹)

-0.61

σιμοποι

-0.61

jeg

-0.59

intérieur

-0.57

POSITIVE LOGITS

 rate

3.37

 rates

3.25

 Rate

3.20

Rate

3.03

 RATE

3.02

 Rates

2.95

Rates

2.77

rate

2.73

 RATES

2.64

RATE

2.63

Activations Density 0.082%

references to rates and their values

No Comments

No Known Activations