INDEX

Explanations

references to the use of resources or systems in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

 using

-1.01

using

-0.80

 USING

-0.68

 Using

-0.66

Using

-0.66

 menggunakan

-0.65

 usando

-0.60

 utilizando

-0.59

use

-0.59

 gebruik

-0.56

POSITIVE LOGITS

 interchangeably

0.98

 sparingly

0.91

 extensively

0.88

 instead

0.84

 wisely

0.79

instead

0.75

ในการ

0.73

 zamiast

0.69

 hyvä

0.67

 вместо

0.66

Activations Density 0.700%

references to the use of resources or systems in various contexts

No Comments

No Known Activations