INDEX

Explanations

instances of the word "review" and its variations

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

academic reviews

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

Mut

-0.38

 Mission

-0.36

Mah

-0.36

 Mahoney

-0.36

 handle

-0.35

〒

-0.35

 Contact

-0.35

ुष

-0.34

 Conta

-0.33

タジー

-0.33

POSITIVE LOGITS

 review

0.88

 reviewing

0.83

review

0.82

Review

0.75

 Review

0.72

REVIEW

0.71

 reviewed

0.70

 Reviewing

0.63

 REVIEW

0.63

 обзор

0.62

Activations Density 0.043%

instances of the word "review" and its variations

academic reviews

No Comments

No Known Activations