INDEX

Explanations

references to the audience or recipients of actions in the text

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

them followed by actions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

":"",

-0.41

"}")

-0.39

ншни

-0.37

variety

-0.36

 ältere

-0.36

 voorkomen

-0.35

sounds

-0.35

"}";

-0.35

各样的

-0.35

Historic

-0.34

POSITIVE LOGITS

 Mereka

0.79

Mereka

0.79

 mereka

0.76

 họ

0.73

their

0.70

他们

0.69

Their

0.69

 their

0.68

他們

0.68

They

0.66

Activations Density 0.027%

references to the audience or recipients of actions in the text

them followed by actions

No Comments

No Known Activations