INDEX

Explanations

adjectives related to capability and visibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

ing

-0.94

 autorytatywna

-0.78

 invokingState

-0.73

LookAnd

-0.73

setupUi

-0.67

SharedCtor

-0.66

tagHelperRunner

-0.63

ually

-0.61

ed

-0.60

ING

-0.60

POSITIVE LOGITS

ObjectModel

0.73

 Touchable

0.71

 outcomes

0.70

 Theſe

0.70

"]="

0.67

ABLE

0.66

keits

0.66

vable

0.63

="@+

0.61

gable

0.61

Activations Density 0.246%

adjectives related to capability and visibility

No Comments

No Known Activations