INDEX

Explanations

references to numerical order and classifications

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

"third" (or "3rd")

np_acts-logits-general · gemini-2.0-flash

third-party and third-world contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

abestanden

-0.72

ksikon

-0.70

 saurait

-0.68

Personensuche

-0.67

parsedMessage

-0.65

 itſelf

-0.60

|}{}

-0.60

 שוליים

-0.59

 Theſe

-0.59

 تضيفلها

-0.58

POSITIVE LOGITS

 place

0.68

arily

0.67

 grade

0.65

 tier

0.65

 Third

0.64

 baseman

0.63

Third

0.60

principalColumn

0.59

aries

0.57

 party

0.57

Activations Density 0.190%

references to numerical order and classifications

"third" (or "3rd")

third-party and third-world contexts

No Comments

No Known Activations