INDEX

Explanations

instances of the word "to" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

windowFixed

-0.95

contentLoaded

-0.94

IndentedString

-0.86

IUrlHelper

-0.82

 ویکی‌پدیای

-0.81

 समीक्षाएं

-0.81

Personensuche

-0.79

awtextra

-0.77

 Мексичка

-0.75

 jspb

-0.73

POSITIVE LOGITS

 take

1.01

be

0.99

 make

0.88

 have

0.81

use

0.78

 spend

0.78

put

0.77

 join

0.77

 engage

0.77

 give

0.75

Activations Density 0.275%

instances of the word "to" in various contexts

No Comments

No Known Activations