INDEX

Explanations

words that indicate emotional responses or reactions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

setVerticalGroup

-0.54

way

-0.50

 best

-0.49

gra

-0.47

hel

-0.47

-0.46

 रा

-0.46

“

-0.46

it

-0.45

POSITIVE LOGITS

 stimulate

1.38

 provoke

1.34

 Stim

1.32

 stimulates

1.29

 stimulated

1.28

 provoked

1.28

 Stimulation

1.26

 stimulating

1.25

 incite

1.25

stimulated

1.21

Activations Density 0.340%

words that indicate emotional responses or reactions

No Comments

No Known Activations