INDEX

Explanations

expressions of agreement or affirmation in conversation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 Amis

-0.62

े

-0.60

Tur

-0.59

yns

-0.58

ężczy

-0.57

 Morin

-0.57

 Treff

-0.56

acar

-0.56

acaktır

-0.55

:///

-0.54

POSITIVE LOGITS

Yeah

1.53

 Yeah

1.52

 YEAH

1.47

 yeah

1.45

yeah

1.38

YEAH

1.31

Yea

0.98

eah

0.98

 outta

0.97

 GONNA

0.93

Activations Density 0.035%

expressions of agreement or affirmation in conversation

No Comments

No Known Activations