INDEX

Explanations

the word "This" in various contexts

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

"this" followed by a noun phrase or verb

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

setVerticalGroup

-0.72

 ujednoznacz

-0.66

LookAnd

-0.66

fortawesome

-0.65

ABUL

-0.63

verwijspagina

-0.63

 uLocal

-0.59

 صوتيه

-0.58

 Administrativna

-0.58

征詢我

-0.58

POSITIVE LOGITS

is

0.69

This

0.66

 This

0.60

has

0.52

was

0.50

 Tämä

0.48

 doesn

0.48

isn

0.47

 wasn

0.43

 would

0.42

Activations Density 0.073%

the word "This" in various contexts

"this" followed by a noun phrase or verb

No Comments

No Known Activations