INDEX

Explanations

prepositions indicating relationships in time or space

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

Formatting and code snippets

np_acts-logits-general · gemini-2.0-flash

diverse character sets and languages

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

帖最后由

-0.78

UnusedPrivate

-0.74

 <>",

-0.71

 createState

-0.71

DebuggerNonUser

-0.68

NameInMap

-0.67

 !!!!

-0.66

 !!!!!!

-0.64

ISupport

-0.64

Jereo

-0.64

POSITIVE LOGITS

wyr

0.69

 itſelf

0.68

énéral

0.65

 your

0.65

ällor

0.60

>`;

0.59

 estético

0.59

Trusted

0.59

eseorang

0.59

 houſe

0.58

Activations Density 0.276%

prepositions indicating relationships in time or space

Formatting and code snippets

diverse character sets and languages

No Comments

No Known Activations