INDEX

Explanations

words expressing positive sentiment or praise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 myſelf

-1.10

 fhew

-1.00

 springfox

-0.98

 itſelf

-0.95

 caucus

-0.93

 fevere

-0.93

bootstrapcdn

-0.93

 Renata

-0.92

 defire

-0.92

 ویکی‌پدیا

-0.90

POSITIVE LOGITS

 good

2.61

good

2.48

 Good

2.40

Good

2.37

 GOOD

2.23

GOOD

2.19

 buena

1.47

 Goodwin

1.38

 gute

1.34

 Goodman

1.28

Activations Density 0.087%

words expressing positive sentiment or praise

No Comments

No Known Activations