INDEX

Explanations

descriptions of high-quality products or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

Wearing

-0.53

äfts

-0.50

 popolazione

-0.50

RequestMapping

-0.49

unculus

-0.49

tomos

-0.49

 Occup

-0.48

 confidentialité

-0.47

[[

-0.47

 rospy

-0.47

POSITIVE LOGITS

 good

1.34

 excellent

1.29

excellent

1.27

good

1.19

 quality

1.19

cellent

1.18

 GOOD

1.11

 Excellent

1.10

quality

1.10

Good

1.09

Activations Density 0.413%

descriptions of high-quality products or services

No Comments

No Known Activations