INDEX

Explanations

negations and their variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

oredCriteria

-0.66

ตัว

-0.63

 Noten

-0.61

mybatisplus

-0.60

jsii

-0.56

-0.55

nader

-0.55

 lượt

-0.55

 guida

-0.53

 AppCompatTheme

-0.52

POSITIVE LOGITS

 commencing

0.69

 AnyObject

0.69

 htons

0.68

BagLayout

0.67

StoryboardSegue

0.64

 metaphor

0.64

 commenced

0.63

Published

0.62

 metaphors

0.62

 Paro

0.62

Activations Density 0.224%

negations and their variations

No Comments

No Known Activations