INDEX

Explanations

first-person pronouns associated with positive sentiment, especially like/love, with some other related words/phrases.

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GHIJKLM

-0.57

PRESA

-0.49

исленность

-0.49

Begriffsklä

-0.49

клопе

-0.49

callee

-0.48

Iné

-0.48

clero

-0.47

|||

-0.47

裟

-0.47

POSITIVE LOGITS

 love

1.35

 loved

1.28

 adore

1.26

 loves

1.17

 adored

1.12

 LOVE

1.08

 LOVED

1.06

 liked

1.05

love

1.03

loved

0.99

Activations Density 0.755%

first-person pronouns associated with positive sentiment, especially like/love, with some other related words/phrases.

No Comments

No Known Activations