INDEX

Explanations

sections that describe application processes or guidelines

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

Writing, editing, or summarizing text

np_acts-logits-general · gemini-2.0-flash

writing and formatting text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 MotionEvent

-0.65

djangoproject

-0.60

urlpatterns

-0.59

heast

-0.54

---*/

-0.53

 snorted

-0.52

delwed

-0.51

ensement

-0.50

PRNewswire

-0.49



-0.49

POSITIVE LOGITS

 writing

0.84

 concise

0.79

 content

0.76

 formatting

0.76

writing

0.75

 summarizing

0.73

 text

0.73

 editing

0.72

 paragraphs

0.72

 Writing

0.72

Activations Density 0.417%

sections that describe application processes or guidelines

Writing, editing, or summarizing text

writing and formatting text

No Comments

No Known Activations