INDEX

Explanations

technical jargon and specific formatting elements common in code or mathematical notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 '\\;'

-0.95

IsContent

-0.82

 myſelf

-0.81

 itſelf

-0.79

 "}";

-0.76

 الحره

-0.76

 Jefus

-0.75

(;;)

-0.73

Efq

-0.72

 مشين

-0.70

POSITIVE LOGITS

<b>

1.48

<strong>

1.29

//

1.12

**

0.83

mathbf

0.82

<!--

0.70

//

0.69

**

0.64

boldsymbol

0.61

{\

0.54

Activations Density 0.544%

technical jargon and specific formatting elements common in code or mathematical notation

No Comments

No Known Activations