INDEX

Explanations

the word "that" 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 @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

verwijspagina

-0.80

 itſelf

-0.78

 estimés

-0.75

Them

-0.70

 ་་

-0.70

 kasarigan

-0.70

stdc

-0.70

MigrationBuilder

-0.70

 propOrder

-0.69

Personensuche

-0.68

POSITIVE LOGITS

 there

1.19

the

1.12

 they

1.06

we

0.90

 although

0.84

 some

0.83

 this

0.81

it

0.81

 neither

0.81

0.80

Activations Density 0.368%

the word "that" in various contexts

No Comments

No Known Activations