INDEX

Explanations

references to individuals and their achievements or statuses in various contexts

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

followed by a form of "be"

np_acts-logits-general · gemini-2.0-flash

related descriptive clauses

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

 betweenstory

-0.82

sizeCache

-0.75

!*\

-0.68

 חיצוניים

-0.65

✨:

-0.60

OGND

-0.59

tvguidetime

-0.59

IntoConstraints

-0.58

:✨

-0.57

 تضيفلها

-0.57

POSITIVE LOGITS

以外にも

0.54

 originally

0.53

 estimated

0.53

=$?

0.52

detectChanges

0.51

He

0.49

age

0.49

 only

0.49

brigens

0.49

 Estimated

0.49

Activations Density 0.397%

references to individuals and their achievements or statuses in various contexts

followed by a form of "be"

related descriptive clauses

No Comments

No Known Activations