INDEX

Explanations

references to exams or testing in an educational context

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

exam and following words

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

\"");

-0.45

 Dinge

-0.45

｀)

-0.44

 Burnett

-0.44

arlı

-0.43

 Manley

-0.43

 Pierce

-0.43

"");

-0.42

 Porter

-0.42

tığı

-0.41

POSITIVE LOGITS

 exam

1.86

 Exam

1.67

Exam

1.63

exam

1.57

 exams

1.55

 Exams

1.52

 EXAM

1.47

exams

1.29

Exams

1.28

 exámenes

0.94

Activations Density 0.006%

references to exams or testing in an educational context

exam and following words

No Comments

No Known Activations