INDEX

Explanations

phrases about being informed or instructed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

OGND

-0.77

enumii

-0.71

Efq

-0.71

 calendriers

-0.69

Чыганаклар

-0.65

 OMITTED

-0.63

namespace

-0.59

 tán

-0.59

 Drapeau

-0.58

mazoo

-0.58

POSITIVE LOGITS

nteral

0.57

 judiciaire

0.53

 otrzy

0.51

 diminta

0.50

 accès

0.47

scriptcase

0.46

接到

0.46

Được

0.46

 acesso

0.46

yii

0.46

Activations Density 0.276%

phrases about being informed or instructed

No Comments

No Known Activations