INDEX

Explanations

negative sentiments or unfavorable outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 avoient

-0.70

ViewFeatures

-0.67

devamını

-0.64

__(/*!

-0.63

})();

-0.62

 <<<<<<<<<<<<<<

-0.60

tvguidetime

-0.59

 EconPapers

-0.59

ukone

-0.59

 étoient

-0.57

POSITIVE LOGITS

GOTREF

0.58

expandindo

0.56

AddTagHelper

0.53

parseFrom

0.53

VIAF

0.53

 createState

0.52

withIdentifier

0.52

 play

0.49

RTEX

0.48

__.__

0.48

Activations Density 0.045%

negative sentiments or unfavorable outcomes

No Comments

No Known Activations