INDEX

Explanations

instances of the word "review" and its various forms

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

"review" or "reviews"

np_acts-logits-general · gemini-2.0-flash

review publications and studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 Dallas

-0.62

-0.60

ματο

-0.58

któ

-0.58

brengen

-0.58

di

-0.55

Nar

-0.55

ICATION

-0.55

-0.54

am

-0.54

POSITIVE LOGITS

 Reviews

1.26

Reviews

1.25

 reviews

1.22

 REVIEWS

1.20

 Review

1.18

REVIEW

1.16

 REVIEW

1.16

PhysRev

1.11

Review

1.11

 review

1.11

Activations Density 0.158%

instances of the word "review" and its various forms

"review" or "reviews"

review publications and studies

No Comments

No Known Activations