INDEX

Explanations

conditional phrases indicating caution or considerations in various contexts

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

BeginContext

-0.50

்கு

-0.48

 padi

-0.45

neurial

-0.44

 thơm

-0.43

 geändert

-0.42

 montré

-0.41

nutie

-0.41

 NgModule

-0.41

prisma

-0.41

POSITIVE LOGITS

RenderAtEndOf

0.83

tvguidetime

0.72

setupUi

0.67

 dealing

0.63

antMatchers

0.63

TintMode

0.63

figsize

0.62

indexPath

0.62

RegressionTest

0.62

 AssemblyTitle

0.61

Activations Density 0.378%

conditional phrases indicating caution or considerations in various contexts

No Comments

No Known Activations