INDEX

Explanations

frequent references to the second person pronouns "you" and "your."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Ades

-0.71

 abel

-0.67

PED

-0.63

 idem

-0.62

ASA

-0.59

 verdi

-0.59

#:

-0.59

Oda

-0.58

 Coch

-0.58

 Kras

-0.57

POSITIVE LOGITS

you

1.69

You

1.64

you

1.60

You

1.58

YOU

1.52

YOU

1.51

we

1.04

Vous

1.01

We

0.98

您

0.97

Activations Density 0.239%

frequent references to the second person pronouns "you" and "your."

No Comments

No Known Activations