INDEX

Explanations

sections of text that contain no meaningful content or information

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

Capital letters followed by numbers

np_acts-logits-general · gemini-2.0-flash

abbreviations, initials

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

TagMode

-0.69

 Signalez

-0.63

ंदीखरीदारी

-0.61

MessageOf

-0.61

NameInMap

-0.60

 OMITBAD

-0.59

setVerticalGroup

-0.58

LookAnd

-0.58

 transfieras

-0.57

 AppCompatTheme

-0.57

POSITIVE LOGITS

eds

0.58



0.54



0.51

tomans

0.49

MigrationBuilder

0.48

ritch

0.46

 którzy

0.46

íncia

0.45

 $\}$

0.45

λίου

0.45

Activations Density 0.286%

sections of text that contain no meaningful content or information

Capital letters followed by numbers

abbreviations, initials

No Comments

No Known Activations